© 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. 63465
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æĭľ
    -0.16
    ék
    -0.16
    rays
    -0.16
     inconsistent
    -0.15
    rists
    -0.15
    etes
    -0.15
    -filled
    -0.15
    æĻ¶
    -0.15
    uyo
    -0.14
    çİĭåºľ
    -0.14
    POSITIVE LOGITS
    è¿«
    0.17
    综èīº
    0.14
    arc
    0.14
    èĢĥéªĮ
    0.14
    æĭ±
    0.14
    ccione
    0.14
    orc
    0.14
    çļĦç¼ĺ
    0.14
    ä¸ĸ代
    0.14
    _arc
    0.14
    Activations Density 0.820%

    No Known Activations

    This feature has no known activations.