© 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. 38044
    Prev
    Next
    INDEX
    Explanations

    number, results, specified

    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
    ä¸įèĻļ
    -0.07
    _COMPILE
    -0.07
     Races
    -0.07
    ä¸ĭåIJĮ
    -0.07
    _fence
    -0.07
    çļĦéĤ£äºĽ
    -0.07
    efeld
    -0.07
    _REDIRECT
    -0.07
    -vars
    -0.06
    éŀŃ
    -0.06
    POSITIVE LOGITS
     specified
    0.09
    specified
    0.07
    &apos
    0.07
    odne
    0.06
    æĮīçħ§è§Ħå®ļ
    0.06
    æĮĩå®ļ
    0.06
    ип
    0.06
    æĺ¯ä¸Ģç§į常è§ģçļĦ
    0.06
    arters
    0.06
    çĴ¨
    0.06
    Activations Density 0.021%

    No Known Activations