© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 41142
    Prev
    Next
    INDEX
    Explanations

    Code or configuration snippets

    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
    æĵįä½ľ
    -0.96
    çļĦæĵįä½ľ
    -0.91
     operation
    -0.91
     operations
    -0.90
     activity
    -0.82
    åĬ¨ä½ľ
    -0.80
     activities
    -0.79
     action
    -0.79
     actions
    -0.77
    æ´»åĬ¨
    -0.77
    POSITIVE LOGITS
    engu
    0.25
     porous
    0.24
    /LICENSE
    0.24
    holm
    0.23
     Sick
    0.23
     enfer
    0.23
     jackpot
    0.22
    fonts
    0.22
    Assistant
    0.22
    ´Ī
    0.22
    Activations Density 0.003%

    No Known Activations