© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 4234
    Prev
    Next
    INDEX
    Explanations

    全て

    np_max-act · gemini-2.0-flash

    header-style professional or promotional taglines and calls to action, especially title-cased phrases separated by symbols like “&” or “|” and similar formal openers across languages.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ashes
    -0.07
    olves
    -0.07
    /load
    -0.07
    log
    -0.07
     Kostenlos
    -0.06
     DST
    -0.06
     возраст
    -0.06
    endency
    -0.06
    られています
    -0.06
    comes
    -0.06
    POSITIVE LOGITS
    ]')↵
    0.07
     shale
    0.07
    物体
    0.07
    AppBar
    0.07
    靶
    0.06
     graphite
    0.06
    `.`
    0.06
    _total
    0.06
     стали
    0.06
     Gabri
    0.06
    Activations Density 0.331%

    No Known Activations