© 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. 41332
    Prev
    Next
    INDEX
    Explanations

    hang, chill

    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
    -picker
    -0.30
     Ñģез
    -0.25
    _parse
    -0.25
     наÑĥÑĩ
    -0.25
    tbl
    -0.24
     redraw
    -0.24
    season
    -0.24
     overflow
    -0.24
     borr
    -0.24
    Overflow
    -0.24
    POSITIVE LOGITS
     hang
    0.74
     hanging
    0.72
     chill
    0.70
    æĮĤ
    0.63
     hangs
    0.62
     chilling
    0.60
     hung
    0.55
    hang
    0.54
     chilled
    0.53
    Hang
    0.52
    Activations Density 0.002%

    No Known Activations