© 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. 56923
    Prev
    Next
    INDEX
    Explanations

    symbols and mathematical structures

    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
    éĢļ常为
    -0.08
    äºĨå¾Īå¤ļ
    -0.07
    æ½ĩ
    -0.07
    éĤ£å¹´
    -0.07
    éĢļ常æĺ¯
    -0.07
    éĢļå¸¸åľ¨
    -0.07
    .selectAll
    -0.06
    åħ¨ä½ĵåħļåijĺ
    -0.06
    å®Įåħ¨åı¯ä»¥
    -0.06
     solito
    -0.06
    POSITIVE LOGITS
    è¦ģä¹Ī
    0.10
     except
    0.08
    éĥ½æľīä¸Ģ个
    0.08
    æĪĸå¤ļæĪĸå°ij
    0.08
    éĥ½æľī
    0.08
     either
    0.08
    OutOfRange
    0.08
    æľīä¸ĢèĤ¡
    0.08
    except
    0.07
     Either
    0.07
    Activations Density 0.008%

    No Known Activations