© 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. 19393
    Prev
    Next
    INDEX
    Explanations

    technical/forum text

    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
    SDL
    -0.27
    achel
    -0.26
    èĢĮåİ»
    -0.25
    optim
    -0.25
    رس
    -0.24
     LL
    -0.24
    便
    -0.24
    iller
    -0.24
    oub
    -0.24
    pres
    -0.24
    POSITIVE LOGITS
     Annual
    0.31
    atile
    0.27
    -win
    0.26
     Vaults
    0.26
    atform
    0.25
    ercul
    0.25
    Annual
    0.25
    大åĨĽ
    0.24
     FOOT
    0.24
    æĢ¯
    0.24
    Activations Density 0.899%

    No Known Activations