© 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. 13257
    Prev
    Next
    INDEX
    Explanations

    bit shifting, href generation, SELECT statements, averaging operations

    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
    è°´
    -0.07
    æĺ¥æļĸèĬ±å¼Ģ
    -0.07
    enner
    -0.07
    antie
    -0.07
    éī
    -0.07
    ®
    -0.07
    laki
    -0.07
    inhos
    -0.07
    ãĤ¿ãĤ¤
    -0.07
    éģĵä¸Ĭ
    -0.07
    POSITIVE LOGITS
     roughly
    0.08
     somehow
    0.08
    ä¼¼æĺ¯
    0.08
    æŁIJç§į
    0.07
     seemingly
    0.07
     infused
    0.07
    æ°ĹãģĮãģĻãĤĭ
    0.07
    ROUGH
    0.07
     somew
    0.07
     Wald
    0.07
    Activations Density 0.160%

    No Known Activations