© 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. 120880
    Prev
    Next
    INDEX
    Explanations

    period

    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
     Napoleon
    -0.07
    CTS
    -0.07
     Utah
    -0.07
     rowIndex
    -0.07
    .osgi
    -0.07
     HMS
    -0.07
    -it
    -0.07
    .ht
    -0.07
     insets
    -0.07
    뿡
    -0.06
    POSITIVE LOGITS
    ,ch
    0.07
    RODUCTION
    0.07
    חסר
    0.07
    (""))↵
    0.07
    ','
    0.07
    aimassage
    0.07
    _answer
    0.07
     """↵
    0.07
    ちょう
    0.07
    ﲠ
    0.07
    Activations Density 0.001%

    No Known Activations