© 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. 32-TRANSCODER-HP
    7. 41922
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unting
    -0.27
     Tigers
    -0.25
     contr
    -0.24
    ãģ¾ãģĹãģ¦
    -0.24
    .validators
    -0.24
    >tag
    -0.23
    OTES
    -0.23
     Tight
    -0.23
    taire
    -0.23
    isin
    -0.23
    POSITIVE LOGITS
    odem
    0.28
    åĮĸè¿Ľç¨ĭ
    0.28
    away
    0.27
    ongan
    0.27
    åĮĸ
    0.27
    æļ´
    0.26
     bek
    0.26
     Danger
    0.26
    odom
    0.26
     fan
    0.25
    Activations Density 0.001%

    No Known Activations