© 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. 19540
    Prev
    Next
    INDEX
    Explanations

    equatorial, tsunami, adenoma, view controllers, sidewall, Afro-Brazilian, Airport Authority, nerve terminals, breech

    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
    emps
    -0.07
    å¤ĸåĽ½è¯ŃåŃ¦æł¡
    -0.07
    <typeof
    -0.06
    Malloc
    -0.06
    对æѤä¸įæī¿æĭħä»»ä½ķ
    -0.06
    åľ¨è¿Ļä¸Ģ
    -0.06
     upstream
    -0.06
     volna
    -0.06
    Clickable
    -0.06
    ÑĤеÑĢÑı
    -0.06
    POSITIVE LOGITS
    nius
    0.07
    æľ¬èº«
    0.07
    离
    0.07
    éŀŃ
    0.07
    æľ¬æĿ¥å°±
    0.07
    æľ¬æĿ¥å°±æĺ¯
    0.07
    æľ¬èº«çļĦ
    0.07
    åij¨åı£
    0.07
    èĩªèº«
    0.07
    ç±»
    0.06
    Activations Density 0.062%

    No Known Activations