© 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. 44055
    Prev
    Next
    INDEX
    Explanations

    or

    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
     three
    -0.34
    three
    -0.29
     two
    -0.29
    _three
    -0.28
     four
    -0.27
     cáºŃn
    -0.27
     deux
    -0.27
     Three
    -0.27
     trois
    -0.27
    -three
    -0.27
    POSITIVE LOGITS
    brit
    0.29
    æĪ·
    0.27
    itel
    0.26
    æĻ¶
    0.26
    night
    0.26
    yı
    0.26
    ä¸Ģ级
    0.26
    ente
    0.26
     sake
    0.25
    preh
    0.24
    Activations Density 0.000%

    No Known Activations