© 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. 56417
    Prev
    Next
    INDEX
    Explanations

    naming conventions and documentation

    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
    ortable
    -0.08
    .qq
    -0.07
    -sized
    -0.07
    æľīæķĪçļĦ
    -0.07
    è¨Ĺ
    -0.06
    åĪ©çļĦ
    -0.06
    çijŁ
    -0.06
    еÑĤен
    -0.06
    olan
    -0.06
    olvers
    -0.06
    POSITIVE LOGITS
     ulang
    0.10
    çļĦåŁºæľ¬åİŁåĪĻ
    0.08
    æĸ¹å¼ı为
    0.08
    éĢļåĪĻ
    0.08
     convention
    0.08
     conventions
    0.08
    åĴĮçIJĨ解
    0.08
    æĥ¯ä¾ĭ
    0.08
    lama
    0.08
    ä½ĵç³»åĴĮ
    0.08
    Activations Density 0.050%

    No Known Activations