© 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. 19987
    Prev
    Next
    INDEX
    Explanations

    public

    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
    æĸĩåĮĸ交æµģ
    -0.27
    exual
    -0.27
    wg
    -0.26
    cid
    -0.25
    Nx
    -0.25
    æĸĩåĮĸ建设
    -0.24
     dominant
    -0.24
    íģIJ
    -0.24
    å¥łåŁº
    -0.24
     Applications
    -0.23
    POSITIVE LOGITS
     support
    0.34
    æĶ¯æĮģ
    0.32
     Support
    0.31
    æ´¾
    0.29
     spirit
    0.29
    æ´ŀ
    0.28
    çIJĨ解åĴĮ
    0.28
    support
    0.28
    Support
    0.28
     approval
    0.27
    Activations Density 0.034%

    No Known Activations