© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 63713
    Prev
    Next
    INDEX
    Explanations

    the

    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
    Not in Any Lists

    No Comments

    Negative Logits
     hạ
    -0.26
     succession
    -0.24
    è£Ķ
    -0.23
     пÑĢаво
    -0.23
    ä¸Ĭåįĩ
    -0.23
    ä¸ĭæĿ¥
    -0.23
    gue
    -0.23
     sche
    -0.23
    è¿ĽæĿ¥
    -0.23
    ANTS
    -0.23
    POSITIVE LOGITS
    æĶ»åĿļ
    0.26
     //~
    0.25
    icum
    0.25
    åħ¼
    0.25
     exposed
    0.25
    uttle
    0.24
     exposing
    0.24
     pr
    0.24
    CTOR
    0.24
    uniq
    0.23
    Activations Density 36.984%

    No Known Activations