© 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. 4408
    Prev
    Next
    INDEX
    Explanations

    experimentally, for instance, limited

    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
    ç¸
    -0.07
    Cart
    -0.06
    èķ´
    -0.06
    ↵
    -0.06
    ier
    -0.06
    ç¥ĸ
    -0.06
    -
    -0.06
    å¼ł
    -0.06
    ç¼
    -0.06
    常人
    -0.06
    POSITIVE LOGITS
     opa
    0.09
    çļĦä¾ĭåŃIJ
    0.09
    åıįè¿ĩæĿ¥
    0.09
    arani
    0.08
     INCIDENTAL
    0.08
    è¿Ļç§įåģļæ³ķ
    0.08
    ترÙĪÙĨ
    0.08
    å°±åı«
    0.08
    ä¹Łç»ı常
    0.08
    otka
    0.08
    Activations Density 0.054%

    No Known Activations