© 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. 20146
    Prev
    Next
    INDEX
    Explanations

    year counts

    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
    cheme
    -0.08
    éĶ¦æ¶Ľ
    -0.07
    æŀŃ
    -0.07
    æĮĸæİĺåħ¬åı¸
    -0.07
    assi
    -0.07
     dipers
    -0.07
    hyl
    -0.07
     muit
    -0.07
    ProcessEvent
    -0.07
    ufer
    -0.07
    POSITIVE LOGITS
    æķ°æį®æĺ¾ç¤º
    0.09
    æĻĤçĤ¹ãģ§
    0.09
    çļĦæķ°æį®æĺ¾ç¤º
    0.08
    ç»Łè®¡æķ°æį®
    0.08
    æĬ¥åijĬæĺ¾ç¤º
    0.08
     statistic
    0.08
    ç»Łè®¡
    0.08
    IMI
    0.07
     itib
    0.07
     data
    0.07
    Activations Density 0.413%

    No Known Activations