© 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. 26480
    Prev
    Next
    INDEX
    Explanations

    same or still

    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
    æĿ¥æºIJäºİç½ij绾
    -0.07
    _OPT
    -0.07
    dir
    -0.06
     finally
    -0.06
     enfin
    -0.06
    éĢįéģ¥
    -0.06
    geist
    -0.06
    áĢĿ
    -0.06
    veille
    -0.06
    pong
    -0.06
    POSITIVE LOGITS
    çħ§æł·
    0.10
     ë§Īì°¬ê°Ģì§Ģ
    0.09
    åıªè¦ģæĺ¯
    0.08
    except
    0.08
    åIJĮæł·çļĦ
    0.08
    ä¾ĿçĦ¶
    0.08
    ä¸įåIJĮçļĦæĺ¯
    0.08
    aras
    0.08
    åıªä¸įè¿ĩ
    0.08
     principles
    0.08
    Activations Density 0.026%

    No Known Activations