© 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. 64637
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    é¦Ĺ
    -0.28
    retrieve
    -0.28
    梢
    -0.28
    褪
    -0.27
    olog
    -0.27
    shared
    -0.27
     shared
    -0.26
    noon
    -0.25
    éĢļ
    -0.25
    .indices
    -0.25
    POSITIVE LOGITS
    laden
    0.30
    grav
    0.28
    ç»ıåķĨ
    0.26
    vier
    0.25
    幸
    0.25
    inux
    0.25
    undler
    0.25
    è¿ĻåĿĹ
    0.24
     {}).
    0.24
     MediaType
    0.24
    Activations Density 25.737%

    No Known Activations