© 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. 45291
    Prev
    Next
    INDEX
    Explanations

    facts about

    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
    æĤī
    -0.09
    rowser
    -0.08
    enko
    -0.08
    fras
    -0.08
    æļĤå®ļ
    -0.08
    oine
    -0.08
    ç»´æĸ¯
    -0.08
     beze
    -0.08
    _ENCODING
    -0.08
    kbd
    -0.08
    POSITIVE LOGITS
    nan
    0.07
    CLASS
    0.06
    na
    0.06
     Ja
    0.06
    -
    0.06
    éĥ½åIJĪ
    0.06
     nan
    0.06
    _
    0.06
     oblig
    0.05
    lite
    0.05
    Activations Density 0.019%

    No Known Activations