© 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. 37965
    Prev
    Next
    INDEX
    Explanations

    there exists

    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
    å¤įåĪ¶æĪĸ
    -0.08
    æīĢ带æĿ¥çļĦ
    -0.08
    tier
    -0.08
    orry
    -0.07
    æľĢç¾İ好çļĦ
    -0.07
    ette
    -0.07
    ovat
    -0.07
    è¿Ļ件
    -0.07
    åħ¶ä¸Ńä¹ĭä¸Ģ
    -0.07
    大ä¼ĹçļĦ
    -0.07
    POSITIVE LOGITS
    åı¯å¾ª
    0.07
    æī¾åĪ°
    0.07
     olyan
    0.07
    èĸ
    0.06
    aff
    0.06
     à¤IJसा
    0.06
     ways
    0.06
    æī¾åĪ°ä¸Ģ个
    0.06
     Ñĥда
    0.06
    æ´ģéĿ¢
    0.06
    Activations Density 0.022%

    No Known Activations