© 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. 44473
    Prev
    Next
    INDEX
    Explanations

    punctuation after expressions

    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
    Negative Logits
    .reject
    -0.07
    aris
    -0.07
     dara
    -0.07
    è¿Ľè¡Į管çIJĨ
    -0.07
    .isDefined
    -0.07
    ç«Ļåľ¨äºĨ
    -0.07
    åľ¨æİ¥ä¸ĭæĿ¥çļĦ
    -0.07
    udel
    -0.07
     tercer
    -0.06
    èĢģå¸ĪåĴĮ
    -0.06
    POSITIVE LOGITS
    åħĪçĶ¨
    0.13
    é¦ĸåħĪ
    0.13
    åħĪ
    0.12
    ãģ¾ãģļ
    0.12
     ÑģнаÑĩала
    0.11
    é¦ĸåħĪåľ¨
    0.11
    åħĪæĺ¯
    0.11
    åħĪå°Ĩ
    0.10
    以ä¸ĭæŃ¥éª¤
    0.10
     먼ìłĢ
    0.10
    Activations Density 0.804%

    No Known Activations