© 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. 32-TRANSCODER-HP
    7. 42570
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¯Ń
    -0.26
     vill
    -0.26
    REV
    -0.25
    ierge
    -0.24
     nik
    -0.24
     untranslated
    -0.24
     LGPL
    -0.24
     abl
    -0.24
     torture
    -0.24
    obox
    -0.24
    POSITIVE LOGITS
    寤
    0.27
    说åĩºæĿ¥
    0.26
    iasm
    0.26
    .getAs
    0.26
    æ¡¡
    0.26
    bows
    0.25
    ieux
    0.25
    éľ²åĩº
    0.25
    å¤ĦçIJĨ
    0.24
    Dispatch
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.