© 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. 51405
    Prev
    Next
    INDEX
    Explanations

    the start of something

    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
    istr
    -0.08
    åĪ°æľŁ
    -0.07
    ãĤĴæ®ĭ
    -0.07
    åĽŀåİ»äºĨ
    -0.07
     maxlength
    -0.07
    åī©ä¸ĭ
    -0.07
    æĺ¥èĬĤæľŁéĹ´
    -0.07
    å®Į
    -0.07
    æİīçļĦ
    -0.06
    èĢĥå¯Ł
    -0.06
    POSITIVE LOGITS
    å¼Ģå§ĭçļĦ
    0.14
    /start
    0.14
    åIJ¯åĬ¨
    0.14
     onset
    0.14
     start
    0.14
    èµ·å§ĭ
    0.14
    çļĦå¼Ģå§ĭ
    0.14
    start
    0.14
    æŃ£å¼ıåIJ¯åĬ¨
    0.14
     ìĭľìŀij
    0.13
    Activations Density 0.592%

    No Known Activations