© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 33122
    Prev
    Next
    INDEX
    Explanations

    I try, open, obtained, derivative, get

    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
    æľīä½ł
    -0.07
    å¿ħãģļ
    -0.06
    ç±»æݨ
    -0.06
     tr
    -0.06
     overlapping
    -0.06
    ÙĪاÙĨ
    -0.06
    乡åİ¿
    -0.06
    #/
    -0.06
    åģ¥åħ¨
    -0.06
    æijĨäºĨ
    -0.06
    POSITIVE LOGITS
     thá»Ń
    0.11
    è¯ķçĿĢ
    0.09
    ä¸Ģåıij
    0.08
    å®ŀçİ°ä¸Ńåįİæ°ijæĹıä¼Łå¤§å¤įåħ´
    0.08
    çİĭæĻĵ
    0.08
    è¯ķè¯ķ
    0.08
    ä¸Ģè¯ķ
    0.08
    !!:
    0.08
    ä¸Ģæĭį
    0.08
     totiž
    0.08
    Activations Density 0.011%

    No Known Activations