© 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. 27-TRANSCODER-HP
    7. 7705
    Prev
    Next
    INDEX
    Explanations

    your or for

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    alled
    -0.29
    ()._
    -0.28
    ä¸ĢåĪĩ
    -0.26
    åĽ´çĿĢ
    -0.25
    为ä¸ŃåĽ½
    -0.25
    -duty
    -0.25
    ç»Ļä½ł
    -0.25
    ä¸ºä½ł
    -0.24
    replace
    -0.24
    ç»Ļä»ĸ
    -0.24
    POSITIVE LOGITS
    é«ĺ涨
    0.25
    å·´æĭī
    0.25
    èĪĴ
    0.24
    è¯ļå®ŀ
    0.24
    ÑģпоÑĢ
    0.24
    ResponseStatus
    0.23
     expression
    0.23
    æĶ¶åĽŀ
    0.23
    è¿Ļå¼ł
    0.23
     lis
    0.23
    Activations Density 0.007%

    No Known Activations