© 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. 49580
    Prev
    Next
    INDEX
    Explanations

    punctuation and questions

    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
    鼷æĸ¯
    -0.09
    èĻ½çĦ¶æ²¡æľī
    -0.08
    зд
    -0.08
    ipsis
    -0.08
    ë¦Ħ
    -0.07
    æĬĵç´§
    -0.07
    èĻ½çĦ¶ä¸įæĺ¯
    -0.07
    ä½Ĩä¸įéĻIJäºİ
    -0.07
    å¦Ĥæ°´
    -0.07
    amac
    -0.07
    POSITIVE LOGITS
    天ä¸Ĭ
    0.08
    åıĪæĬĬ
    0.07
    å°±åıĪ
    0.07
    rames
    0.07
    åıĪ被
    0.06
    è¦ģçľĭ
    0.06
    åıĪ
    0.06
    æĽ´ç¬¦åIJĪ
    0.06
    éĤ£æŶåĢĻ
    0.06
    å¸ĥçļĦ
    0.06
    Activations Density 0.003%

    No Known Activations