© 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. 128977
    Prev
    Next
    INDEX
    Explanations

    heritage

    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
    åŃ©
    -0.25
    tile
    -0.25
    nett
    -0.25
     endregion
    -0.24
    nings
    -0.24
    ért
    -0.24
    ohn
    -0.24
    饼
    -0.24
    lico
    -0.24
    зд
    -0.23
    POSITIVE LOGITS
    å¿ĺ
    0.28
     epochs
    0.27
    éĻ¢éĻ¢å£«
    0.25
    æĹģ
    0.25
     itself
    0.25
    æĺİç¡®æıIJåĩº
    0.25
     fres
    0.25
    èĸ°
    0.25
    anity
    0.25
    é²ľæĺİ
    0.25
    Activations Density 6.252%

    No Known Activations