© 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. 12675
    Prev
    Next
    INDEX
    Explanations

    path names

    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
    vl
    -0.08
    IDD
    -0.07
    odne
    -0.07
    nyt
    -0.07
     شا
    -0.07
    _ANS
    -0.07
    од
    -0.07
    odin
    -0.07
    noop
    -0.06
    大éĢļ
    -0.06
    POSITIVE LOGITS
    ä¹Łåı¯ä»¥éĢļè¿ĩ
    0.09
    itas
    0.08
    ä¹Łåı¯çĽ´æİ¥
    0.07
     alternatively
    0.07
     posix
    0.07
    æī§
    0.07
    å®ĺ
    0.06
    ä¹Łåı¯ä»¥åľ¨
    0.06
    ä¼łç»Ł
    0.06
    æīĭåĬ¨
    0.06
    Activations Density 0.054%

    No Known Activations