© 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. 12739
    Prev
    Next
    INDEX
    Explanations

    open circuit, open state

    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
    åºķèķ´
    -0.08
     Lower
    -0.08
    Lower
    -0.08
    åİĭåĪ¶
    -0.08
    éĻįä½İ
    -0.08
    ãģıãģł
    -0.07
    رض
    -0.07
    ä½İè°ĥ
    -0.07
    示èĮĥåŁºåľ°
    -0.07
    èĢĮä¸ĭ
    -0.07
    POSITIVE LOGITS
    ä¸įéĢļ
    0.10
     isolation
    0.09
    æĸŃè·¯
    0.08
     upstream
    0.08
    éĺ»æĸŃ
    0.08
    æĸŃå¼Ģ
    0.08
    æħ§èģª
    0.08
    ä¸Ń空
    0.08
    çĻ
    0.08
    æĸŃ
    0.07
    Activations Density 0.006%

    No Known Activations