© 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. 8551
    Prev
    Next
    INDEX
    Explanations

    successful history responsive worthy overview steps focus

    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
    æĿĤ
    -0.07
    lement
    -0.07
    éĿŀåIJĮ
    -0.07
    çİ°å°±
    -0.07
    çļĩçĶ«
    -0.07
    isel
    -0.06
    è¿ŀåIJĮ
    -0.06
    ilt
    -0.06
    ľ
    -0.06
     неп
    -0.06
    POSITIVE LOGITS
    缸åħ³æݨèįIJ
    0.08
    æŃ¤æ¥¼
    0.08
    armo
    0.07
    IDAS
    0.07
    ÙĢÙĢÙĢÙĢÙĢ
    0.07
    æĤ¨çİ°åľ¨çļĦä½įç½®
    0.07
    ÐļÐIJÐĶ
    0.07
    cÄħ
    0.07
     Artik
    0.07
    æĤ¨å°Ĩ
    0.07
    Activations Density 0.011%

    No Known Activations