© 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. 41701
    Prev
    Next
    INDEX
    Explanations

    trademark, MasterCard, Unicode, basketball

    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
    ingan
    -0.09
    ingar
    -0.08
    elet
    -0.08
    vrier
    -0.08
    qli
    -0.08
    awatan
    -0.08
    erah
    -0.08
    æ°´åİ¿
    -0.08
    ezza
    -0.08
    ingin
    -0.08
    POSITIVE LOGITS
    çķĶ
    0.08
    ä¹ĭçĪ¶
    0.08
    æĺ¯æĪijåĽ½
    0.07
    ÑĥÑĤÑĮ
    0.07
    çļĦ
    0.07
    mp
    0.07
    åıĬåħ¶
    0.06
    ires
    0.06
    æľµæľµ
    0.06
    ий
    0.06
    Activations Density 0.007%

    No Known Activations