© 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. 1824
    Prev
    Next
    INDEX
    Explanations

    logistic regression

    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
     Hancock
    -0.08
    ÙĦÙĪد
    -0.08
    åİŁæľī
    -0.07
    ä¹ĭéķ¿
    -0.07
     conceivable
    -0.07
    osz
    -0.07
    æĻķ
    -0.07
    ilding
    -0.07
    czas
    -0.07
    raq
    -0.07
    POSITIVE LOGITS
    å¸ĥå°Ķ
    0.07
    æŀķ
    0.07
    æľĽ
    0.07
    ickle
    0.07
    ÙĬات
    0.07
    witz
    0.07
    ellent
    0.07
    çļĦ好
    0.07
    Ø¢Ùħد
    0.06
    Viewport
    0.06
    Activations Density 0.002%

    No Known Activations