© 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. 31-TRANSCODER-HP
    7. 19616
    Prev
    Next
    INDEX
    Explanations

    Descriptions of things

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å·¦
    -0.37
     Left
    -0.35
     left
    -0.31
    -left
    -0.30
    _left
    -0.29
    .left
    -0.28
    Left
    -0.28
    ,left
    -0.28
    :left
    -0.28
    RING
    -0.28
    POSITIVE LOGITS
     thought
    0.35
     finished
    0.28
     finish
    0.27
     basket
    0.27
    彩
    0.26
    atars
    0.26
    æĺı
    0.25
    ä¹ĭä½Ļ
    0.25
     fast
    0.25
    utow
    0.25
    Activations Density 1.646%

    No Known Activations