© 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. 57845
    Prev
    Next
    INDEX
    Explanations

    lesson plan

    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
    åĩºèµĦ
    -0.09
    stens
    -0.08
    年度æĬ¥åijĬ
    -0.08
    夫æĸ¯åŁº
    -0.07
    å¹´éī´
    -0.07
    æ¯ıåŃ£åº¦
    -0.07
    çĻ½çļ®ä¹¦
    -0.07
    .qual
    -0.07
    éļıåľ°
    -0.07
    å·¥åķĨä¸ļ
    -0.07
    POSITIVE LOGITS
    æݢ究
    0.09
    åľ¨æķĻåѦä¸Ń
    0.08
    é¢Ħæ¡Ī
    0.08
    esel
    0.08
    -hook
    0.08
    æĪijçıŃ
    0.08
     allotted
    0.07
    导
    0.07
    è¿ĻèĬĤ课
    0.07
    éĩįåľ¨
    0.07
    Activations Density 0.003%

    No Known Activations