© 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. 9783
    Prev
    Next
    INDEX
    Explanations

    legal and definitional terms

    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
    æ¯Ķäºļ
    -0.08
    жеÑĤ
    -0.07
    èĢĮå¦Ĥä»Ĭ
    -0.07
    主åĬĽèµĦéĩij
    -0.06
    è¿«
    -0.06
    ä¸įåı¯æĪĸ缺çļĦ
    -0.06
    inton
    -0.06
    rum
    -0.06
    缸å½ĵ大çļĦ
    -0.06
     Stéph
    -0.06
    POSITIVE LOGITS
    æľīä¸ĭåĪĹ
    0.11
    ä»ĺ款æĸ¹å¼ı
    0.10
    åıĮæĸ¹çļĦ
    0.10
    åıĮæĸ¹
    0.09
    对ä¸Ĭè¿°
    0.09
    ä¹Ļæĸ¹
    0.08
    åıĮæĸ¹åľ¨
    0.08
    ä¸įåı¯æĬĹ
    0.08
    ä»»ä½ķä¸Ģæĸ¹
    0.08
    æľīä¸ĭåĪĹæĥħå½¢ä¹ĭä¸ĢçļĦ
    0.08
    Activations Density 0.007%

    No Known Activations