© 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. 108547
    Prev
    Next
    INDEX
    Explanations

    on

    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
    ä¸įä¸ĭ
    -0.30
    åħ·
    -0.30
    achen
    -0.27
    ank
    -0.26
    kit
    -0.26
    çī¢
    -0.26
    å¥Ĺ
    -0.26
    åºľ
    -0.25
    åıĺ
    -0.25
    åĩºèĩª
    -0.25
    POSITIVE LOGITS
    ero
    0.29
    odef
    0.28
    ataire
    0.27
     Dante
    0.26
    èĩ³æĸ¼
    0.25
    éĢĨè¡Į
    0.25
    ç§Ģ丽
    0.25
    è°ģçŁ¥éģĵ
    0.24
     metres
    0.24
    鸱
    0.24
    Activations Density 2.527%

    No Known Activations