© 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. 41783
    Prev
    Next
    INDEX
    Explanations

    code and technical jargon

    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
     dead
    -0.80
    dead
    -0.74
     Dead
    -0.66
    æŃ»
    -0.65
    Dead
    -0.62
     DEAD
    -0.57
    .dead
    -0.55
    (dead
    -0.55
    _dead
    -0.53
     mort
    -0.50
    POSITIVE LOGITS
    ircular
    0.31
    æīĭä¸Ĭ
    0.28
    çijĽ
    0.27
    centers
    0.25
    ikes
    0.24
     Glow
    0.24
     Circular
    0.23
    é²ģ
    0.23
    çŁ¿çī©
    0.23
    boo
    0.23
    Activations Density 0.003%

    No Known Activations