© 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. 62252
    Prev
    Next
    INDEX
    Explanations

    mathematical and scientific constants

    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
    akup
    -0.07
    æģĻ
    -0.07
    è²Į
    -0.06
    éen
    -0.06
    _since
    -0.06
    kontrol
    -0.06
    ìĦŃ
    -0.06
    å©ķ
    -0.06
     Juda
    -0.06
    _("
    -0.06
    POSITIVE LOGITS
    é£İè¡Į
    0.07
    roe
    0.07
    .hy
    0.07
    urus
    0.07
    compile
    0.07
    åĸľ
    0.07
    ãĤ¯ãĥŃãĤ¹
    0.07
    é£İ湿
    0.06
    家åºŃåĮ»çĶŁ
    0.06
    èģĺ
    0.06
    Activations Density 0.001%

    No Known Activations