© 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. 12-TRANSCODER-HP
    7. 23477
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸ĵ线
    -0.29
    ä¸ĢåĪ»
    -0.27
    DW
    -0.27
    æĹ¢è¦ģ
    -0.26
     sake
    -0.26
    FTA
    -0.25
     candidacy
    -0.25
    WI
    -0.25
    Candidates
    -0.25
    ä¸įå¿į
    -0.25
    POSITIVE LOGITS
     brilliance
    0.29
    /linux
    0.28
    ->_
    0.25
    è¥Ł
    0.25
    åľ¨æł¡
    0.25
    骧
    0.24
    éĢģåĩº
    0.24
     Glory
    0.24
     tapping
    0.24
     moll
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.