© 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. 40977
    Prev
    Next
    INDEX
    Explanations

    questions

    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
    Negative Logits
     campaigned
    -0.31
    è¦ģä¹Ī
    -0.27
     Upon
    -0.27
    attended
    -0.26
     Either
    -0.26
    esses
    -0.26
     propose
    -0.25
     offers
    -0.25
     proposes
    -0.24
     seizing
    -0.24
    POSITIVE LOGITS
     once
    0.36
     while
    0.32
    .Should
    0.31
    Once
    0.29
    ä¸įåºĶ
    0.28
    [email
    0.27
    åıĬ缸åħ³
    0.27
     should
    0.27
    once
    0.27
    >You
    0.27
    Activations Density 0.003%

    No Known Activations