© 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. 18393
    Prev
    Next
    INDEX
    Explanations

    code/calculations

    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
    ImageContext
    -0.27
    èµ·
    -0.26
     nameof
    -0.25
    laden
    -0.25
    åĬĽè¿ĺæĺ¯
    -0.24
    encing
    -0.24
    ayed
    -0.23
     image
    -0.23
    acent
    -0.23
    LinkId
    -0.23
    POSITIVE LOGITS
     Contract
    0.28
    ets
    0.27
    shaft
    0.26
    ans
    0.25
     contracts
    0.25
    ç®Ń
    0.24
    CEF
    0.24
     ans
    0.24
    Dic
    0.24
    å¥ij约
    0.24
    Activations Density 0.022%

    No Known Activations