© 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. 107583
    Prev
    Next
    INDEX
    Explanations

    code

    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
     composition
    -0.30
     Mang
    -0.29
     composing
    -0.29
     mang
    -0.28
    development
    -0.26
    æŀĦæĪIJ
    -0.26
    ç»ĦæĪIJ
    -0.25
     compos
    -0.25
     reform
    -0.25
    ç»ĦæĪIJçļĦ
    -0.25
    POSITIVE LOGITS
    èĭ¥æĤ¨
    0.30
    pot
    0.27
    +":
    0.25
    ä»įåľ¨
    0.25
    endors
    0.25
    "|
    0.25
    yor
    0.25
    elib
    0.24
     anonymously
    0.24
     Pot
    0.24
    Activations Density 5.238%

    No Known Activations