© 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. 49040
    Prev
    Next
    INDEX
    Explanations

    United Arab Emirates

    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
    é½IJ
    -0.07
    没
    -0.07
    utul
    -0.07
    æŃĮ
    -0.06
    ure
    -0.06
    åĩ»
    -0.06
    继
    -0.06
    ->
    -0.06
    åį³
    -0.06
    uring
    -0.06
    POSITIVE LOGITS
    ermo
    0.08
    ä¸īé«ĺ
    0.08
    ä¹ĺæľº
    0.08
    ä¸įè¿ĩæĿ¥
    0.08
    åłĤçļĩ
    0.07
    imme
    0.07
    .removeItem
    0.07
    fru
    0.07
    ä½łä»¬æĺ¯
    0.07
    nette
    0.07
    Activations Density 0.001%

    No Known Activations