© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 18292
    Prev
    Next
    INDEX
    Explanations

    the

    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
    Negative Logits
    文旅
    -0.07
     fullWidth
    -0.07
    تحميل
    -0.07
    逭
    -0.07
    制品
    -0.07
    翯
    -0.07
    ">\
    -0.07
    rello
    -0.07
     ")↵
    -0.07
    贯彻落实
    -0.07
    POSITIVE LOGITS
     améric
    0.07
     diabetic
    0.07
    ＊
    0.06
    两名
    0.06
     מיוחד
    0.06
     slashing
    0.06
    retty
    0.06
    _rules
    0.06
     Louise
    0.06
     gab
    0.06
    Activations Density 0.017%

    No Known Activations