© 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. 41885
    Prev
    Next
    INDEX
    Explanations

    Common short words

    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
    ED
    -0.25
     nowrap
    -0.25
     anymore
    -0.24
    奢
    -0.24
     textStyle
    -0.24
    èĮ§
    -0.24
    ç¹ģ
    -0.24
    .xlim
    -0.24
    ErrorHandler
    -0.24
    ymb
    -0.24
    POSITIVE LOGITS
    ç°ª
    0.25
    以èī²
    0.25
    uits
    0.25
    wb
    0.24
     wing
    0.24
     wag
    0.24
     Sour
    0.24
    TO
    0.24
    actics
    0.24
    ales
    0.24
    Activations Density 0.003%

    No Known Activations