© 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. 46071
    Prev
    Next
    INDEX
    Explanations

    peer review

    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
    seg
    -0.07
    ĵĴ
    -0.07
    讼
    -0.07
    ãģ¶ãĤĬ
    -0.07
    ame
    -0.07
    ihan
    -0.07
    æļ¢
    -0.07
    浩çĦ¶
    -0.06
    éral
    -0.06
    __/
    -0.06
    POSITIVE LOGITS
    sic
    0.07
    强è°ĥçļĦæĺ¯
    0.07
    mods
    0.07
    ppers
    0.06
    Ìģ
    0.06
    λιÏĥ
    0.06
     grundsätzlich
    0.06
    inz
    0.06
     Heim
    0.06
     fundamentally
    0.06
    Activations Density 0.225%

    No Known Activations