© 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. 16263
    Prev
    Next
    INDEX
    Explanations

    compare, differences, distinguish

    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
    è²Ĥ
    -0.07
    æİĽ
    -0.07
    idos
    -0.07
    çĮ¿
    -0.07
    ecu
    -0.07
     dangling
    -0.06
    dac
    -0.06
    hur
    -0.06
    ç»Ķ
    -0.06
     Dunia
    -0.06
    POSITIVE LOGITS
    ç»Łè®¡åѦ
    0.11
     differences
    0.11
     statistically
    0.10
     distributions
    0.10
    åĿĩåĢ¼
    0.09
     difference
    0.09
    å·®å¼Ĥ
    0.09
     Unterschiede
    0.09
     Differences
    0.09
    æ¯Ķè¾ĥæľī
    0.09
    Activations Density 0.174%

    No Known Activations