© 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. 9338
    Prev
    Next
    INDEX
    Explanations

    attached the

    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
    çļĦè¦ģ
    -0.07
    ukkit
    -0.07
    ঢ
    -0.07
    olls
    -0.06
    hq
    -0.06
    åį´ä¹Ł
    -0.06
    æīĢ以è¦ģ
    -0.06
    ÙĪÙĨس
    -0.06
    ä»ħä»£è¡¨ä½ľèĢħ
    -0.06
    åıĪ以
    -0.06
    POSITIVE LOGITS
     демон
    0.09
    iamo
    0.07
    åľ¨æĥ³
    0.07
    à¸ĵ
    0.07
    iero
    0.07
    emon
    0.07
    åľ¨éĺħ读
    0.07
    yam
    0.07
    Demon
    0.07
    åľ¨åĴĮ
    0.07
    Activations Density 0.001%

    No Known Activations