© 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. 9075
    Prev
    Next
    INDEX
    Explanations

    always

    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
    æ¯ıä¸Ģ个ç»ĨèĬĤ
    -0.08
     suddenly
    -0.08
    uddenly
    -0.08
    äºŁå¾ħ
    -0.07
    æĸ¹æĸ¹éĿ¢éĿ¢
    -0.07
     Ùħب
    -0.07
     Cald
    -0.07
     already
    -0.07
    å®Įåħ¨ä¸įåIJĮçļĦ
    -0.07
    å¾Ģå¾Ģä¼ļ
    -0.07
    POSITIVE LOGITS
     تÙĤرÙĬب
    0.13
     except
    0.12
    éĻ¤éĿŀ
    0.11
     regardless
    0.11
    except
    0.11
     Except
    0.10
     sauf
    0.10
    Except
    0.10
     unless
    0.09
     Regardless
    0.09
    Activations Density 0.049%

    No Known Activations