© 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. 29073
    Prev
    Next
    INDEX
    Explanations

    sentence end 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
    æķ¬è¯·æľŁå¾ħ
    -0.09
    è¿Ļ家åħ¬åı¸
    -0.08
    rie
    -0.08
    umbang
    -0.07
    åIJij被åijĬ
    -0.07
    á´
    -0.07
    æŃ¤äºº
    -0.07
    欢è¿İåħ³æ³¨
    -0.07
    ertiary
    -0.07
    rieve
    -0.07
    POSITIVE LOGITS
    ä¸Ģæĸ¹éĿ¢
    0.10
    å®ĥä¸įä»ħ
    0.09
    éĢļè¿ĩ对
    0.09
    å¦Ĥåľ¨
    0.08
    åı¦ä¸Ģæĸ¹éĿ¢
    0.08
    ä¸Ģæĺ¯
    0.08
    çī¹åĪ«æĺ¯åľ¨
    0.08
    åĢ¼å¾Ĺä¸ĢæıIJçļĦæĺ¯
    0.08
    åĿļæĮģ以
    0.08
    ç«ĭ足
    0.08
    Activations Density 0.040%

    No Known Activations