© 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. 1496
    Prev
    Next
    INDEX
    Explanations

    programming context

    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
    overs
    -0.08
    软åĮĸ
    -0.07
    hra
    -0.07
    åįĬæŃ¥
    -0.07
    æľīç¼ĺ
    -0.07
     oversh
    -0.07
    ovil
    -0.07
    ariat
    -0.07
     qual
    -0.07
    åľºåĿĩ
    -0.07
    POSITIVE LOGITS
    èĨ³
    0.07
    perc
    0.07
    æ¨
    0.07
     lug
    0.07
    navbar
    0.07
    ner
    0.07
    .extern
    0.06
    çļĦå¥½ä¹łæĥ¯
    0.06
     contributions
    0.06
    ughter
    0.06
    Activations Density 0.001%

    No Known Activations