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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 19-RESID-POST-AA
    11. 5963
    Prev
    Next
    INDEX
    Explanations

    generated or written

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    尤其
    -0.07
     sic
    -0.07
    uela
    -0.07
    ững
    -0.07
    ﮆ
    -0.07
    ="{{$
    -0.06
     guest
    -0.06
     Jinping
    -0.06
     esa
    -0.06
     tre
    -0.06
    POSITIVE LOGITS
    燃煤
    0.07
     grav
    0.07
     migraine
    0.07
     mining
    0.07
    BF
    0.07
    により
    0.07
    קר
    0.06
     enumeration
    0.06
     firearm
    0.06
     Portland
    0.06
    Activations Density 0.001%

    No Known Activations