© 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. 30870
    Prev
    Next
    INDEX
    Explanations

    parentheses and numbers

    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
     nig
    -0.07
    çĶ©
    -0.07
     bún
    -0.07
    ضÙħÙĨ
    -0.07
    乡åİ¿
    -0.07
    éĴĪ
    -0.06
    æĸĩçIJĨ
    -0.06
    ductor
    -0.06
    ç¯Ģ
    -0.06
    ìłĪ
    -0.06
    POSITIVE LOGITS
    ä»İ严治
    0.08
    é£İè¡Į
    0.08
    uding
    0.07
    å¤ļå¾Ĺ
    0.07
     Pedi
    0.07
    çŃ¹
    0.07
     Dodd
    0.07
    hots
    0.06
     Dolphin
    0.06
    alan
    0.06
    Activations Density 0.011%

    No Known Activations