© 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. 32289
    Prev
    Next
    INDEX
    Explanations

    evaluation and analysis suffixes

    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
    commended
    -0.08
    fru
    -0.08
    åĴĮçłĶ究
    -0.07
    ÑĨен
    -0.07
    éģĹçĹĩ
    -0.07
    çģ«åĢĻ
    -0.07
    ĭ
    -0.06
    åŁºæĿIJ
    -0.06
    eneg
    -0.06
    llib
    -0.06
    POSITIVE LOGITS
     analysis
    0.11
     tests
    0.11
    æµĭè¯ķ
    0.09
    tests
    0.09
    åĪĨæŀIJä¸İ
    0.09
     testing
    0.09
    _test
    0.08
     test
    0.08
     analyses
    0.08
    _tests
    0.08
    Activations Density 0.602%

    No Known Activations