© 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. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 130902
    Prev
    Next
    INDEX
    Explanations

    scientific studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    äºĨåIJĹ
    -0.24
    icket
    -0.24
     model
    -0.24
    模åŀĭ
    -0.23
    ,model
    -0.23
    çĽ¸äº²
    -0.23
     RADIO
    -0.23
     FAST
    -0.23
     AngularFire
    -0.23
    ANA
    -0.22
    POSITIVE LOGITS
    thal
    0.27
     sessions
    0.26
    alse
    0.25
    stras
    0.25
    åİ»
    0.24
    ÑĥÑĩ
    0.24
    isten
    0.24
    èĤĦ
    0.23
     OCC
    0.23
    _oc
    0.23
    Activations Density 19.622%

    No Known Activations