© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44138
    Prev
    Next
    INDEX
    Explanations

    there is a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĨŁæĤīäºĨ
    -0.07
    åĽłä¸ºå®ĥ们
    -0.07
    çĶ±åIJĦ
    -0.07
    ħĮ
    -0.06
    èµ
    -0.06
    åĽłä¸ºæĪij们
    -0.06
    åĽłä¸ºå®ĥ
    -0.06
    åĽłä¸ºä»ĸ们
    -0.06
    åĽłä¸ºè¿ĻäºĽ
    -0.06
    loge
    -0.06
    POSITIVE LOGITS
    使å¾Ĺ
    0.11
     à¤IJसा
    0.09
     بØŃÙĬØ«
    0.08
     satisfying
    0.08
    æĿ¥æ»¡è¶³
    0.08
    hô
    0.07
    ãģĮãģĤãģ£ãģ¦
    0.07
    éļĶ
    0.07
     existed
    0.07
     <![
    0.07
    Activations Density 0.080%

    No Known Activations