© 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. 10342
    Prev
    Next
    INDEX
    Explanations

    definitions and synonyms

    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
    PRETTY
    -0.07
    å¾ĹçĽĬ
    -0.07
    ä¸įçŁ¥éģĵ该
    -0.07
    ä¹Łä¸įå¤ļ
    -0.07
    .format
    -0.07
    afil
    -0.07
    details
    -0.07
    ¤íĥ
    -0.06
    alls
    -0.06
    eyJ
    -0.06
    POSITIVE LOGITS
     synonym
    0.12
    åIJįè¯į
    0.11
    è¿Ļ个è¯į
    0.11
    æľ¯è¯Ń
    0.11
     synonyms
    0.11
     synonymous
    0.11
     coined
    0.10
    çĶ¨èªŀ
    0.10
     definition
    0.10
    åIJ«ä¹ī
    0.10
    Activations Density 0.063%

    No Known Activations