© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 33838
    Prev
    Next
    INDEX
    Explanations

    few solutions

    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
    家åºĹ
    -0.06
    åĵªäºĽæĸ¹éĿ¢
    -0.06
    lite
    -0.06
    ä¸ĭæĿ¥
    -0.06
    å¥łå®ļåŁºç¡Ģ
    -0.06
    å¼Ģåı£éģĵ
    -0.06
    rest
    -0.06
    å¥łå®ļäºĨåŁºç¡Ģ
    -0.06
    é¢ĺ为
    -0.06
    ä¸Ģ个åı«
    -0.06
    POSITIVE LOGITS
     pula
    0.09
    имо
    0.08
    éŃĶæľ¯
    0.08
    illeur
    0.08
    annis
    0.07
    .updateDynamic
    0.07
    å°¤åħ¶
    0.07
    ä¹Łç¡®å®ŀ
    0.07
    -Jun
    0.07
    ä¸į代表
    0.07
    Activations Density 0.342%

    No Known Activations