© 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. 41721
    Prev
    Next
    INDEX
    Explanations

    technical/reference documents

    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
    VEST
    -0.30
    .blob
    -0.27
    cxx
    -0.27
     buys
    -0.26
    tell
    -0.26
    velle
    -0.26
    velt
    -0.25
    å¥Ħ
    -0.25
     fur
    -0.25
    lingen
    -0.25
    POSITIVE LOGITS
    æ°´åĪĨ
    0.28
    -flash
    0.27
    uart
    0.27
    Gu
    0.26
     Kan
    0.24
    `(
    0.24
     Kon
    0.24
    flash
    0.24
    _post
    0.23
    verages
    0.23
    Activations Density 0.002%

    No Known Activations