© 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. 17730
    Prev
    Next
    INDEX
    Explanations

    water

    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
    Negative Logits
     Academic
    -0.28
    åŃ¦æľ¯
    -0.27
    tagName
    -0.27
     accus
    -0.24
    Canonical
    -0.24
    ellij
    -0.24
    vell
    -0.24
    벨
    -0.24
    wiÄĻ
    -0.24
    _pulse
    -0.24
    POSITIVE LOGITS
     recreation
    0.32
     discharge
    0.31
     Recreation
    0.28
    ri
    0.28
    æĿĤ
    0.28
    ç¨Ģ
    0.28
    Bins
    0.28
    gem
    0.27
     xlink
    0.27
    æİĢ
    0.26
    Activations Density 0.364%

    No Known Activations