© 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. 19984
    Prev
    Next
    INDEX
    Explanations

    technical/scientific documents

    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
    该åī§
    -0.27
    roma
    -0.26
    ipy
    -0.26
    -Isl
    -0.26
    åĸª
    -0.25
    ä¸ĸä¿Ĺ
    -0.24
     restraining
    -0.24
    æ¦Ń
    -0.24
    catalog
    -0.24
    anno
    -0.23
    POSITIVE LOGITS
    _ground
    0.29
     Wind
    0.28
    æݨå¼Ģ
    0.27
    iona
    0.27
    .flatten
    0.27
     navigation
    0.26
    /navigation
    0.26
     MST
    0.26
     navig
    0.26
    é¼»
    0.26
    Activations Density 1.006%

    No Known Activations