© 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. 30-TRANSCODER-HP
    7. 96138
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itarian
    -0.29
    åı¦ä¸ĢåįĬ
    -0.27
    isoft
    -0.27
    æľĢéļ¾
    -0.26
     hardest
    -0.26
    zman
    -0.25
    è¿ĩ渡
    -0.25
    æ´Ĺ礼
    -0.24
    åĭ¤
    -0.24
    /q
    -0.24
    POSITIVE LOGITS
    per
    0.28
    Advertisements
    0.28
    Som
    0.27
     reels
    0.27
    achs
    0.27
     perce
    0.26
    reon
    0.26
    ì²Ļ
    0.26
    è¡ĮçĤº
    0.26
    pace
    0.26
    Activations Density 0.882%

    No Known Activations

    This feature has no known activations.