© 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. 21407
    Prev
    Next
    INDEX
    Explanations

    designs, elementary, essay, media

    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
    rown
    -0.08
    irs
    -0.06
    èįIJ
    -0.06
     ste
    -0.06
     lẫn
    -0.06
     sc
    -0.06
    tering
    -0.06
    sc
    -0.06
    /cgi
    -0.06
    人æīĭ
    -0.06
    POSITIVE LOGITS
    éĢŁéĢĴ
    0.08
    ä¹į
    0.07
     ÑĥÑĢе
    0.07
    عدÙĦ
    0.07
    üg
    0.07
    åı¯èĥ½ä¼ļ对
    0.07
    StackTrace
    0.07
     cref
    0.07
    adop
    0.07
    ä¸ŃåĽ½äººå¯¿
    0.07
    Activations Density 0.074%

    No Known Activations