© 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. 24-TRANSCODER-HP
    7. 151168
    Prev
    Next
    INDEX
    Explanations

    customer service/assistance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     own
    -0.27
    è¿Ļ次
    -0.27
    own
    -0.27
    ç»ĻåĪ«äºº
    -0.27
     &$
    -0.26
     Own
    -0.26
     Jens
    -0.26
    ingroup
    -0.25
    äºĨèĩªå·±çļĦ
    -0.25
    çݰ象
    -0.25
    POSITIVE LOGITS
    æĤ¨åı¯ä»¥
    0.29
    ä½Ļ
    0.26
     permalink
    0.26
    åĮ»éĻ¢
    0.26
    é¤ĺ
    0.26
    ä¸ĢæŦ
    0.26
    Rem
    0.26
    MMC
    0.25
     architect
    0.25
     anytime
    0.25
    Activations Density 0.135%

    No Known Activations