© 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. 41857
    Prev
    Next
    INDEX
    Explanations

    features and insights

    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
    chtest
    -0.07
    Äħcz
    -0.07
    issa
    -0.06
     سرا
    -0.06
    egel
    -0.06
     обÑĭ
    -0.06
    .bd
    -0.06
    ãģ©ãģ¡ãĤīãĤĤ
    -0.06
    èĩªçĦ¶æĺ¯
    -0.06
    esses
    -0.06
    POSITIVE LOGITS
    åħ·æľī以ä¸ĭ
    0.19
    æľī以ä¸ĭ
    0.18
    以ä¸ĭåĩłçĤ¹
    0.17
    以ä¸ĭåĩłä¸ª
    0.16
    以ä¸ĭåĩłä¸ªæĸ¹éĿ¢
    0.16
    æľīä¸ĭåĪĹ
    0.15
    以ä¸ĭåĩł
    0.14
    以ä¸ĭãģ®
    0.13
    以ä¸ĭåĩłç§į
    0.13
    æĢ»ç»ĵå¦Ĥä¸ĭ
    0.13
    Activations Density 0.254%

    No Known Activations