© 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. 20614
    Prev
    Next
    INDEX
    Explanations

    same

    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
    ä¾ĿçĦ¶
    -0.08
    ÑĨвеÑĤа
    -0.08
    áĥŃ
    -0.08
    ormais
    -0.08
    it
    -0.07
    akup
    -0.07
    ãģ¿ãģŁãģĦãģª
    -0.07
    ä¸İæĹ¶ä¿±è¿Ľ
    -0.07
    .fil
    -0.07
    ä¸įæģ¯
    -0.07
    POSITIVE LOGITS
    åIJĮä¸Ģ
    0.08
    еÑĪ
    0.08
    åĴĮåįķä½į
    0.07
    à¹Ģà¸Ķียวà¸ģัà¸Ļ
    0.07
    antar
    0.07
    jsonp
    0.07
    è¿ľè¿ij
    0.07
    åľ¨åIJĮä¸Ģ
    0.07
    åIJĮä¸Ģ个
    0.07
    igan
    0.07
    Activations Density 0.039%

    No Known Activations