© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 60029
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and code delimiting punctuation

    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
    æĽ´ç²¾å½©
    -0.07
    å¦Ĥæ¶īåıĬ
    -0.07
    avit
    -0.07
     ì§Ģì¼ľ
    -0.07
    è¿Ļæł·çļĦäºĭæĥħ
    -0.07
    触
    -0.07
    ä»ħ代表
    -0.07
    ache
    -0.07
    çĢļ
    -0.07
    触åıĬ
    -0.07
    POSITIVE LOGITS
    è¿IJ转
    0.07
    trum
    0.06
    è¿IJè¡Į
    0.06
    sembl
    0.06
    äºŁå¾ħ
    0.06
    ượn
    0.06
    à¸ķà¹īà¸Ńà¸ĩหา
    0.06
    monkey
    0.06
    å¥ķ
    0.06
    éĶĻ
    0.06
    Activations Density 0.036%

    No Known Activations