© 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. 131110
    Prev
    Next
    INDEX
    Explanations

    range

    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
    åĺĺ
    -0.31
    ORIZ
    -0.28
    ONUS
    -0.27
    _notifier
    -0.26
    olini
    -0.26
    è¿°èģĮ
    -0.26
    è¿ĺåĮħæĭ¬
    -0.26
     disclaimer
    -0.25
    _zoom
    -0.25
    (withIdentifier
    -0.24
    POSITIVE LOGITS
    ียà¸Ļ
    0.26
    cko
    0.25
    ertainment
    0.25
    梢
    0.25
    icie
    0.25
    æĽ¿
    0.25
    ç¬Ħ
    0.25
    ervas
    0.24
     Morrow
    0.24
    ensation
    0.23
    Activations Density 10.100%

    No Known Activations