© 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. 22-TRANSCODER-HP
    7. 98987
    Prev
    Next
    INDEX
    Explanations

    periods and numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idents
    -0.27
    acy
    -0.27
    åĤ¬
    -0.27
    çĪ±åĽ½
    -0.27
    æģ©
    -0.24
    xit
    -0.24
    èľļ
    -0.24
    ierung
    -0.24
     Dich
    -0.23
    pond
    -0.23
    POSITIVE LOGITS
    å¤ļä½Ļ
    0.28
    /latest
    0.27
    hausen
    0.26
    ä¸ĢæĿ¡
    0.26
    çĽijè§Ĩ
    0.26
    ophile
    0.25
    ä¸Ģæ¢Ŀ
    0.25
    ä¸Ģ份
    0.23
     vs
    0.23
    /resources
    0.23
    Activations Density 0.073%

    No Known Activations