© 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. 26471
    Prev
    Next
    INDEX
    Explanations

    punctuations, comma, and 'too'

    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
     whatsoever
    -0.08
     absolutamente
    -0.08
     assolutamente
    -0.08
    olutely
    -0.08
     excellence
    -0.07
     unequiv
    -0.07
    æŶå¿ħé¡»
    -0.07
    没æľīä»»ä½ķ
    -0.07
    絶対ãģ«
    -0.07
     абÑģолÑİÑĤно
    -0.07
    POSITIVE LOGITS
    ä¹Łåı¯èĥ½
    0.14
    ä¹Łåı¯èĥ½æĺ¯
    0.13
    ä¹Łæľīåı¯èĥ½
    0.11
     depending
    0.11
    æľªå¿ħ
    0.10
    depending
    0.10
     possibly
    0.10
    ä¹Łè®¸ä¼ļ
    0.10
    æĪĸ许æĺ¯
    0.09
    ä¹Łè®¸æĺ¯
    0.09
    Activations Density 0.156%

    No Known Activations