© 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. 62482
    Prev
    Next
    INDEX
    Explanations

    chapter numbers and articles

    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
    -prev
    -0.09
    è·¯å°ıåѦ
    -0.08
    enums
    -0.08
    åıįæŃ£
    -0.07
    orit
    -0.07
    áĥIJáĥ®
    -0.07
     phong
    -0.07
    .none
    -0.07
    isert
    -0.07
    æĬij
    -0.06
    POSITIVE LOGITS
     titled
    0.09
     entitled
    0.07
    enn
    0.07
    tron
    0.07
     "
    0.07
     nämlich
    0.06
    ell
    0.06
    ä¸ĵéŨ
    0.06
    主é¢ĺ为
    0.06
    æľīåħ³äºİ
    0.06
    Activations Density 0.111%

    No Known Activations