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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1314
    Prev
    Next
    INDEX
    Explanations

    ential

    np_max-act · gemini-2.0-flash
    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
     mish
    -0.07
    רתי
    -0.07
    憋
    -0.07
     DE
    -0.07
    _mi
    -0.07
     Fischer
    -0.07
     dared
    -0.07
    (distance
    -0.07
    .Ch
    -0.07
     любом
    -0.07
    POSITIVE LOGITS
    -haspopup
    0.07
    首家
    0.07
    .way
    0.07
     nominate
    0.07
     очеред
    0.07
    扦
    0.07
    柔软
    0.07
    做起
    0.07
     açıs
    0.06
     Nacional
    0.06
    Activations Density 0.000%

    No Known Activations