© 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. 19324
    Prev
    Next
    INDEX
    Explanations

    say "the"

    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
     online
    -0.30
     ONLINE
    -0.29
    Online
    -0.28
     Online
    -0.28
    åľ¨çº¿
    -0.28
    æīĭæĦŁ
    -0.27
    èѦ
    -0.26
    ãĤªãĥ³ãĥ©ãĤ¤ãĥ³
    -0.25
     digital
    -0.25
     Digital
    -0.24
    POSITIVE LOGITS
    æī¿æİ¥
    0.28
    cca
    0.26
    è¾¹ç¼ĺ
    0.26
    è¾¹éĻħ
    0.26
    æĸ¯åĿ¦
    0.25
    benh
    0.25
    ERCHANT
    0.24
    Ñīен
    0.24
     verk
    0.24
    otel
    0.24
    Activations Density 0.004%

    No Known Activations