© 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. 10434
    Prev
    Next
    INDEX
    Explanations

    specific example or note

    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
    args
    -0.08
    dic
    -0.08
    æĴħ
    -0.08
    åĮĸä½ľ
    -0.07
    rico
    -0.07
    éģģ
    -0.06
    lags
    -0.06
    ildo
    -0.06
    fail
    -0.06
     Defense
    -0.06
    POSITIVE LOGITS
    è§Ħ磩
    0.09
    åľ¨ä¸įåIJĮçļĦ
    0.07
    è¤Ĵ
    0.07
     zufolge
    0.06
    oux
    0.06
    åħ¨éĿ¢æıIJé«ĺ
    0.06
    @a
    0.06
    elah
    0.06
    lb
    0.06
    æŶ令
    0.06
    Activations Density 0.058%

    No Known Activations