© 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. 41267
    Prev
    Next
    INDEX
    Explanations

    desirable to

    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
    åħ¨èº«çļĦ
    -0.08
    æīĢæľīçļĦ人
    -0.08
    èĪ¬åľ°
    -0.08
    apult
    -0.08
    ×ķ×ij×Ķ
    -0.08
    åħ¨éĿ¢èIJ½å®ŀ
    -0.07
    ONOM
    -0.07
    авли
    -0.07
    ãģĤãģı
    -0.07
    tova
    -0.07
    POSITIVE LOGITS
     sometimes
    0.12
    éļ¾åħį
    0.11
     often
    0.11
     Sometimes
    0.10
    æľīæŶ
    0.10
    ç»ı常ä¼ļ
    0.10
    å¾Ģå¾Ģæĺ¯
    0.10
    å¾Ģå¾Ģ
    0.10
     inevitably
    0.10
    æľīæŶåĢĻ
    0.10
    Activations Density 1.722%

    No Known Activations