© 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. 19376
    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
     microseconds
    -0.27
    iband
    -0.27
    -years
    -0.26
    ymbols
    -0.26
     kilometers
    -0.25
    ılma
    -0.25
    _micro
    -0.25
    icro
    -0.25
     Micro
    -0.24
    _seconds
    -0.24
    POSITIVE LOGITS
    åľ¨çİ°åľº
    0.27
    åľ¨è¿Ļç§į
    0.27
     [-
    0.26
     springs
    0.25
    atal
    0.25
    éĻ°
    0.24
    DOI
    0.24
    æĮĩ导ä¸ĭ
    0.24
     rá»iji
    0.23
     rag
    0.23
    Activations Density 1.546%

    No Known Activations

    This feature has no known activations.