© 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. 92419
    Prev
    Next
    INDEX
    Explanations

    missing

    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
    tile
    -0.07
     Mayweather
    -0.07
    bate
    -0.06
    ternal
    -0.06
    ;;
    -0.06
    ובר
    -0.06
     đậu
    -0.06
     Gast
    -0.06
     görd
    -0.06
    —from
    -0.06
    POSITIVE LOGITS
    经营范围
    0.07
    _cases
    0.07
    少许
    0.07
    IClient
    0.06
    北路
    0.06
     rif
    0.06
    _LE
    0.06
     '\\'
    0.06
    鳓
    0.06
    /log
    0.06
    Activations Density 0.006%

    No Known Activations