© 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. 30905
    Prev
    Next
    INDEX
    Explanations

    display math LaTeX

    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
    ä¸Ĭè¿°äºĭå®ŀ
    -0.08
    anst
    -0.08
    efore
    -0.08
     anyways
    -0.08
    ↵      ↵
    -0.08
    ä¸Ĭè¿°ä½ľåĵģ
    -0.07
    æīĢæľīè¿ĻäºĽ
    -0.07
    erv
    -0.07
    è¿ĻçĤ¹
    -0.07
    åIJĮä¸Ĭ
    -0.07
    POSITIVE LOGITS
    é¦ĸåħĪéľĢè¦ģ
    0.06
    bor
    0.06
    PURE
    0.06
    दà¥Ģ
    0.06
    eson
    0.06
    è¶ģçĿĢ
    0.06
    å¸ĮæľĽå¯¹å¤§å®¶æľīæīĢ帮åĬ©
    0.06
    aisons
    0.06
    -bs
    0.06
    缮æłĩæĺ¯
    0.06
    Activations Density 0.023%

    No Known Activations