© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2776
    Prev
    Next
    INDEX
    Explanations

    intrigue, predict, homeless, sunny, round

    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
    Ñıд
    -0.07
    æĪ·æĪ·
    -0.07
    elson
    -0.07
    lak
    -0.07
    æĸ¹éĿ¢çļĦçŁ¥è¯Ĩ
    -0.07
    arder
    -0.07
    kers
    -0.07
    erve
    -0.07
    sgi
    -0.07
    roken
    -0.07
    POSITIVE LOGITS
    äºİ人
    0.08
    ä¸İæĮijæĪĺ
    0.07
    aled
    0.07
    åĨį说
    0.07
    并举
    0.07
    管çIJĨçŃī
    0.07
    ä¸įè¿ĺ
    0.07
    度é«ĺ
    0.06
    ä¼Ĺ
    0.06
    èĢĮå·²
    0.06
    Activations Density 0.039%

    No Known Activations