© 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. 9203
    Prev
    Next
    INDEX
    Explanations

    style and layout elements

    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
    quirrel
    -0.07
    ASIL
    -0.07
    à°Łà±į
    -0.07
    ToFront
    -0.07
    eldorf
    -0.07
    æŶæĬ¥
    -0.07
    ä¹ĭå¿ĥ
    -0.07
    -fat
    -0.06
    æĻ¨æĬ¥
    -0.06
    å½Ĵ纳
    -0.06
    POSITIVE LOGITS
    odes
    0.08
    roits
    0.07
    çģµåĦ¿
    0.07
    æn
    0.07
    anz
    0.07
    CIO
    0.07
    rial
    0.06
    åŃIJéĩĮ
    0.06
    ocket
    0.06
    	inline
    0.06
    Activations Density 0.014%

    No Known Activations