© 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. 7556
    Prev
    Next
    INDEX
    Explanations

    behind a bin

    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
     appunto
    -0.13
    ä¸ĭåIJĮ
    -0.07
    icona
    -0.06
     cli
    -0.06
    ãģ©ãģĵãĤį
    -0.06
    åį³ä¾¿å¦ĤæѤ
    -0.06
    æĬ¼
    -0.06
    å°Ķå¤ļ
    -0.06
     Certo
    -0.06
    æľ¬æĸĩå°Ĩä»İ
    -0.06
    POSITIVE LOGITS
    ãģĵãĤĮãĤĤ
    0.08
    enez
    0.07
    å·¥ä½ľæŶ
    0.07
    ÏĦαν
    0.07
    åıijçİ°åľ¨
    0.07
    _BLE
    0.07
    ä¹Łæĺ¯ä¸ª
    0.07
    رÙĪس
    0.07
    å¯¹åľ¨
    0.07
    ãģĵãģ¡ãĤīãĤĤ
    0.07
    Activations Density 0.191%

    No Known Activations