© 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. 30665
    Prev
    Next
    INDEX
    Explanations

    file extensions and code snippets

    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
     muz
    -0.08
     incapable
    -0.08
    è¿Ļæł·æĤ¨å°±åı¯ä»¥
    -0.07
    æīįå¾Ĺ以
    -0.07
    åıĺ为
    -0.07
    adir
    -0.07
     Protagon
    -0.07
    æĸ°éĹ»ç½ij
    -0.07
    æīĢ以就
    -0.07
    .creator
    -0.06
    POSITIVE LOGITS
    类似çļĦ
    0.08
    æľīåħ³äºİ
    0.08
    è¿Ļæĸ¹éĿ¢çļĦ
    0.07
    æľīåħ³
    0.07
    æĪĸ许æľī
    0.07
    çļĦ缸åħ³åĨħ容
    0.07
    缸åħ³åĨħ容
    0.07
     relevant
    0.07
    æĪĸèĢħåħ¶ä»ĸ
    0.07
    æĪĸèĢħæĺ¯
    0.07
    Activations Density 0.015%

    No Known Activations