© 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. 7708
    Prev
    Next
    INDEX
    Explanations

    xml namespace declarations

    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
    室åĨħ空æ°Ķ
    -0.08
    UnitTest
    -0.08
    å¼ĢéŨ
    -0.07
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.07
    å¦ĤçĥŁ
    -0.07
    åįĹéŨ
    -0.07
    æ¼±
    -0.07
    _logger
    -0.07
    /logger
    -0.07
    inness
    -0.07
    POSITIVE LOGITS
    xsd
    0.07
    åįļ大
    0.07
    _CLASSES
    0.06
    é¦ĸæ¬¡åľ¨
    0.06
    abbrev
    0.06
    bog
    0.06
     ars
    0.06
    _VER
    0.06
    ords
    0.06
    æĺŃ
    0.06
    Activations Density 0.230%

    No Known Activations