© 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. 22682
    Prev
    Next
    INDEX
    Explanations

    numbers following "than"

    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
     exact
    -0.07
     exactly
    -0.07
     precis
    -0.06
    -0.06
     eighty
    -0.06
    ç°
    -0.06
     (
    -0.06
    äºĶåįĥ
    -0.06
    ãģ³
    -0.06
    ingue
    -0.06
    POSITIVE LOGITS
    æ¼ĶçļĦ
    0.09
    Ĥ¹
    0.09
    ׳×Ļ×Ļ×Ŀ
    0.09
    æĬķèµĦæĪĸ
    0.09
    æľīæĿĥä¿ĿçķĻ
    0.08
    serter
    0.08
    ĥ½
    0.08
    ä¸īåĽĽ
    0.08
    å·®ä¸į
    0.08
    éĶĻ误æĪĸ
    0.08
    Activations Density 0.061%

    No Known Activations