© 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. 40646
    Prev
    Next
    INDEX
    Explanations

    existing or non-existing state

    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
    åıijå±ķä¸İ
    -0.08
    åħ¬åı¸ä¸İ
    -0.07
    人被
    -0.07
    é£İåIJ¹è¿ĩ
    -0.07
    åħ¬åı¸åIJij
    -0.07
    å·¥ä½ľä¸İ
    -0.07
    валÑĮ
    -0.06
     bowiem
    -0.06
    WithContext
    -0.06
    åįķä½įåıĤåĬł
    -0.06
    POSITIVE LOGITS
    æĶ¶èĹıæľ¬ç«Ļ
    0.09
     unsus
    0.08
    existing
    0.08
    åĩĨå¤ĩ好çļĦ
    0.08
     otherwise
    0.08
     existing
    0.08
    -existing
    0.07
     similarly
    0.07
    åĪĻ表示
    0.07
    comings
    0.07
    Activations Density 0.409%

    No Known Activations