© 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. 7935
    Prev
    Next
    INDEX
    Explanations

    separate, separately

    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
    bat
    -0.07
    æĢªä¸įå¾Ĺ
    -0.07
    éĩİ
    -0.07
    IOS
    -0.06
    æĻĸ
    -0.06
     Dil
    -0.06
     ex
    -0.06
    end
    -0.06
    乡
    -0.06
    æĺ¯å½ĵåīį
    -0.06
    POSITIVE LOGITS
     separately
    0.12
     оÑĤделÑĮно
    0.11
     separate
    0.11
    åįķçĭ¬çļĦ
    0.10
    ä¸ĵ项
    0.10
     seperate
    0.10
    ä¿Ŀè¯ģåħ¶
    0.10
    ä¸ĵ项治çIJĨ
    0.09
     оÑĤделÑĮ
    0.09
     specialized
    0.09
    Activations Density 0.283%

    No Known Activations