© 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. 18606
    Prev
    Next
    INDEX
    Explanations

    companies, services, marketplaces

    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
    æĿIJæĸĻçļĦ
    -0.07
    -0.07
    æķ¬
    -0.07
    æĸ°æĿIJæĸĻ
    -0.07
    ÙĨدÙĩ
    -0.06
    夫
    -0.06
    è¢«ä¾ĽåºĶåķĨ
    -0.06
     Preparation
    -0.06
    æĿIJæĸĻ
    -0.06
    å¤įæŁ¥
    -0.06
    POSITIVE LOGITS
    为çĶ¨æĪ·æıIJä¾Ľ
    0.12
    çĶ¨æĪ·
    0.10
    为æ¶Īè´¹èĢħ
    0.10
    çĶ¨æĪ·ä½ĵéªĮ
    0.10
     users
    0.10
     user
    0.10
    为çĶ¨æĪ·
    0.09
     monet
    0.09
    对çĶ¨æĪ·
    0.09
    å®ļä»·
    0.09
    Activations Density 0.421%

    No Known Activations