© 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. 12596
    Prev
    Next
    INDEX
    Explanations

    scholarly, collaborative, maturity, international, entertaining, honesty, worldwide

    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
    lessly
    -0.07
    mites
    -0.07
    ?$
    -0.07
     Hearth
    -0.07
    ä¹ĭ说
    -0.07
    penas
    -0.07
    oka
    -0.07
    iza
    -0.07
    çŁ¥ä¹ĭ
    -0.07
    ä¾Ŀ次为
    -0.07
    POSITIVE LOGITS
    ãģªãĤĭãģ¹ãģı
    0.08
    æĹ¢è¦ģ
    0.07
    NN
    0.07
    orig
    0.07
    atric
    0.06
    edig
    0.06
    褶
    0.06
    ounty
    0.06
     Nh
    0.06
    ä¸įç»Ŀ
    0.06
    Activations Density 0.004%

    No Known Activations