© 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. 50430
    Prev
    Next
    INDEX
    Explanations

    drawing labels or photographs

    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
    åIJİæĤĶ
    -0.08
    ç»ĵæŀľæĺ¯
    -0.07
    оÑı
    -0.07
     cannons
    -0.07
    丰å¯ĮäºĨ
    -0.07
    اÙħÙĨ
    -0.07
    åĢ¼æĺ¯
    -0.07
    chter
    -0.07
    èĦ
    -0.06
    çªģå¦Ĥåħ¶
    -0.06
    POSITIVE LOGITS
    æıIJéĨĴèĩªå·±
    0.10
    便äºİ
    0.09
     handy
    0.08
    æĸ¹ä¾¿
    0.08
    æ²ŁéĢļ
    0.08
    éĨĴ缮
    0.08
     remind
    0.08
     reminds
    0.08
    以便
    0.08
    elper
    0.08
    Activations Density 0.073%

    No Known Activations