© 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. 45823
    Prev
    Next
    INDEX
    Explanations

    Hooke's Law, Le Chatelier's principle

    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
    doc
    -0.07
    emer
    -0.07
    onga
    -0.07
    èĩ´çļĦ
    -0.07
    elic
    -0.07
    engel
    -0.07
    大åĪ©
    -0.07
    éĿ¢ç§¯çº¦
    -0.07
    strup
    -0.06
    çīĩä¸Ń
    -0.06
    POSITIVE LOGITS
    æĸ¹æ³ķæĿ¥
    0.07
    å¾Ĺä¸Ģ
    0.07
     *__
    0.07
    åĪĻ表示
    0.07
    æĪij们å°Ĩä¼ļ
    0.07
    >>>>>>>
    0.06
    å¦Ĥæĺ¯
    0.06
    nown
    0.06
    åĪĨæŀIJæ³ķ
    0.06
    '||
    0.06
    Activations Density 0.049%

    No Known Activations