© 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. 19846
    Prev
    Next
    INDEX
    Explanations

    one

    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
    ä¸Ģå¥Ĺ
    -0.27
    æĽ³
    -0.27
    ãģĽãģĦ
    -0.26
    ropol
    -0.26
    âĸ¼
    -0.25
     Armstrong
    -0.25
    etur
    -0.25
    æĬ¥éħ¬
    -0.24
    çļĦä¸Ģ款
    -0.24
    çļĦä¸Ģéĥ¨åĪĨ
    -0.24
    POSITIVE LOGITS
    ONE
    0.44
    หà¸Ļ
    0.40
    one
    0.40
     One
    0.38
    One
    0.38
     ONE
    0.35
    _one
    0.35
    ona
    0.35
    ¹
    0.34
    ä¸Ģ人
    0.34
    Activations Density 50.421%

    No Known Activations