© 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. 18752
    Prev
    Next
    INDEX
    Explanations

    this kind of language

    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
    è¿Ļæł·æĤ¨å°±åı¯ä»¥
    -0.13
    ly
    -0.09
    è¿Ļç§įäºĭæĥħ
    -0.09
    è¿Ļæĺ¯ä¸ª
    -0.09
    è¿ĻæĹłçĸij
    -0.09
    ä½Ĩè¿Ļç§į
    -0.09
    è¿Ļä¸ĭ
    -0.08
    æľīè¿Ļæł·
    -0.08
    è¿Ļæł·å°±åı¯ä»¥
    -0.08
    éĤ£ä»ĸ
    -0.08
    POSITIVE LOGITS
    -ci
    0.10
     ultimi
    0.08
    icismo
    0.08
    /th
    0.08
    ed
    0.07
    à¹ģหละ
    0.07
    çļĦä¸ĢåĪĩéĥ½
    0.07
    że
    0.07
    ory
    0.07
     beiden
    0.07
    Activations Density 0.002%

    No Known Activations