© 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. 43438
    Prev
    Next
    INDEX
    Explanations

    Punctuation

    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
    mond
    -0.34
    ManagerInterface
    -0.29
    çļĦ第ä¸Ģ个
    -0.25
     Full
    -0.25
    Since
    -0.24
    bbing
    -0.24
    çļĦ第ä¸Ģ
    -0.24
    bung
    -0.24
    çļĦèī¯å¥½
    -0.24
     Since
    -0.24
    POSITIVE LOGITS
    .Please
    0.32
    请
    0.31
     please
    0.31
    PLEASE
    0.30
    è¯·ä½ł
    0.30
     Please
    0.29
     below
    0.29
    ToF
    0.28
    ï¼Į请
    0.28
     PLEASE
    0.27
    Activations Density 0.000%

    No Known Activations