© 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. 43120
    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
    uze
    -0.30
    rese
    -0.28
    alogy
    -0.28
    [source
    -0.27
    IAL
    -0.27
    (Pos
    -0.26
    arcer
    -0.26
    éĤ£æ¬¡
    -0.26
    UGC
    -0.25
    WAYS
    -0.25
    POSITIVE LOGITS
    inc
    0.32
    _Write
    0.30
    Inc
    0.29
    rotein
    0.28
     inc
    0.28
     writes
    0.28
    rote
    0.28
    _inc
    0.28
    icus
    0.27
    opl
    0.26
    Activations Density 0.000%

    No Known Activations