© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63936
    Prev
    Next
    INDEX
    Explanations

    health and body actions

    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
    ød
    -0.07
    æ²īé»ĺ
    -0.07
    åIJijåħļ
    -0.07
    åIJijæĪij们
    -0.07
    éķ¿çĽ¸
    -0.07
    å¸Īé£İ
    -0.06
    å¹´å¹´
    -0.06
    æĽ¿
    -0.06
     underage
    -0.06
    afka
    -0.06
    POSITIVE LOGITS
    è½»æŁĶ
    0.09
    åĪºæ¿ĢæĢ§
    0.09
    室åĨħå¤ĸ
    0.09
    ä½Ĩä¸įè¦ģ
    0.09
    åĬĽæīĢèĥ½åıĬ
    0.08
     gently
    0.08
    ä¸ºå®ľ
    0.08
    å°½éĩı
    0.08
    室温
    0.08
    åºĶå°½éĩı
    0.08
    Activations Density 0.013%

    No Known Activations