© 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. 19173
    Prev
    Next
    INDEX
    Explanations

    Computer code

    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
    leitung
    -0.28
    aterno
    -0.28
    è¿Ľ
    -0.28
    atern
    -0.27
    inx
    -0.27
    antics
    -0.26
     @[
    -0.26
    öz
    -0.25
    è°¨
    -0.25
    ç¬ij容
    -0.25
    POSITIVE LOGITS
     stabil
    0.29
     ва
    0.27
    ç¿»å¼Ģ
    0.26
    -Fi
    0.26
    ensi
    0.26
    mnop
    0.25
     stiff
    0.25
    IFF
    0.25
    opa
    0.25
    Manifest
    0.24
    Activations Density 19.525%

    No Known Activations