© 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. 41163
    Prev
    Next
    INDEX
    Explanations

    Legal contexts and names

    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
    éĨī
    -0.30
    vents
    -0.29
    üz
    -0.26
    	Mat
    -0.26
    MS
    -0.26
     selling
    -0.25
     Math
    -0.25
    omid
    -0.24
    Mat
    -0.24
    math
    -0.24
    POSITIVE LOGITS
    åŃIJ
    0.27
    ç§ijåѦéĻ¢
    0.25
    ãĤµ
    0.25
    åŃIJéĩĮ
    0.25
    次
    0.25
     decks
    0.25
    亥
    0.25
    bron
    0.25
    iset
    0.25
    è¿Ļ个è¯į
    0.24
    Activations Density 0.002%

    No Known Activations