© 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. 12234
    Prev
    Next
    INDEX
    Explanations

    count values

    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
    egend
    -0.07
    éĿŀ常大çļĦ
    -0.07
    èĮ¹
    -0.07
    ierer
    -0.07
    éĿŀ常é«ĺçļĦ
    -0.07
    è¾ĥéķ¿çļĦ
    -0.06
    第äºĮçĻ¾äºĶ
    -0.06
    -priced
    -0.06
    edik
    -0.06
    edia
    -0.06
    POSITIVE LOGITS
    æķ°éĩı
    0.17
    æĢ»æķ°
    0.16
    çļĦæķ°éĩı
    0.15
    æķ¸éĩı
    0.15
     count
    0.15
    æķ°çĽ®
    0.15
    æķ°éĩıçļĦ
    0.14
    æķ°
    0.13
    æķ°éĩı为
    0.13
    个æķ°
    0.13
    Activations Density 0.057%

    No Known Activations