© 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. 19205
    Prev
    Next
    INDEX
    Explanations

    end of sentence punctuation

    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
    俺
    -0.07
    éĢļ常
    -0.07
     usually
    -0.07
     basically
    -0.07
    éĢļ常为
    -0.06
    סת
    -0.06
    č↵
    -0.06
    æł¹æį®éľĢè¦ģ
    -0.06
    ce
    -0.06
    éĢļ常ä¼ļ
    -0.06
    POSITIVE LOGITS
    å¸Ĥ人æ°ijæ³ķéĻ¢
    0.08
    è¯Ŀ
    0.08
    zal
    0.08
    ливо
    0.08
    æĽ´ä½ķåĨµ
    0.08
    åĪĨ页
    0.08
    ä½ķåĨµ
    0.07
    à¸ĺุ
    0.07
     Reserved
    0.07
    åĩºå±Ģ
    0.07
    Activations Density 0.692%

    No Known Activations