© 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. 19079
    Prev
    Next
    INDEX
    Explanations

    Code and formulas

    np_max-act-logits · gemini-2.0-flash
    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
     surf
    -0.35
     surface
    -0.30
    表
    -0.28
    åı¯æł¹æį®
    -0.28
    表éĿ¢
    -0.28
     shall
    -0.28
     ÄijÆ°Æ¡ng
    -0.27
    _surface
    -0.26
    åıijå±ķæĪĺçķ¥
    -0.26
    表éĿ¢ä¸Ĭ
    -0.26
    POSITIVE LOGITS
    æ·¹
    0.27
     wis
    0.26
    icum
    0.26
    lli
    0.25
    MapView
    0.25
    MIT
    0.25
    unist
    0.25
    .writeInt
    0.25
    ctype
    0.25
    太平
    0.24
    Activations Density 0.008%

    No Known Activations