© 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. 31-TRANSCODER-HP
    7. 18525
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     occasion
    -0.25
    羧
    -0.25
    ODE
    -0.25
    nev
    -0.24
     prov
    -0.24
     iterate
    -0.24
    alties
    -0.23
    ç¯ģ
    -0.23
    epad
    -0.23
    ç®´
    -0.23
    POSITIVE LOGITS
    æĿ¡
    0.28
    ServiceProvider
    0.27
    Imports
    0.27
    æĶ¿
    0.26
    rs
    0.24
    è¿ĻæĿ¡
    0.24
    èĤī
    0.24
    Workers
    0.24
    มà¸ĩ
    0.24
    chl
    0.23
    Activations Density 12.617%

    No Known Activations

    This feature has no known activations.