© 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. 49818
    Prev
    Next
    INDEX
    Explanations

    saponins

    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
    templ
    -0.07
    eks
    -0.07
    æĭįæĪı
    -0.07
    ieval
    -0.07
    ospace
    -0.07
    èĴ¸èĴ¸æĹ¥ä¸Ĭ
    -0.07
    avra
    -0.06
    åIJŀ
    -0.06
    odka
    -0.06
     signs
    -0.06
    POSITIVE LOGITS
    åIJ«éĩı
    0.11
    åIJ«éĩıé«ĺ
    0.10
     extracted
    0.10
    çļĦåIJ«éĩı
    0.10
    åIJ«éĩıçļĦ
    0.09
    åĪĨåŃIJéĩı
    0.09
    æıIJåıĸ
    0.09
    extract
    0.08
    found
    0.08
    对人ä½ĵ
    0.08
    Activations Density 0.278%

    No Known Activations