© 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. 28627
    Prev
    Next
    INDEX
    Explanations

    :

    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
     hydrogen
    -0.07
     suff
    -0.07
    +(
    -0.07
     ambiguous
    -0.07
    _YES
    -0.07
     Neither
    -0.06
     بدا
    -0.06
    しか
    -0.06
    ไกล
    -0.06
     carga
    -0.06
    POSITIVE LOGITS
     Sequential
    0.08
    PYTHON
    0.08
     Rockefeller
    0.08
    .mapbox
    0.08
     onChangeText
    0.07
     tokenizer
    0.07
    otide
    0.07
    ancock
    0.07
     цены
    0.07
    политическ
    0.07
    Activations Density 0.001%

    No Known Activations