© 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. 20094
    Prev
    Next
    INDEX
    Explanations

    dialogue/lists

    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
     Byz
    -0.07
     Literature
    -0.07
     breathe
    -0.06
     TOM
    -0.06
    .layoutControlItem
    -0.06
    '});↵
    -0.06
    bye
    -0.06
    oad
    -0.06
    ocytes
    -0.06
    ㄚ
    -0.06
    POSITIVE LOGITS
    看过
    0.07
    ..........
    0.07
    (service
    0.07
     getField
    0.07
    Neighbor
    0.07
    dzi
    0.07
    _receiver
    0.06
    はじ
    0.06
    ביע
    0.06
     syncing
    0.06
    Activations Density 0.047%

    No Known Activations