© 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. 13826
    Prev
    Next
    INDEX
    Explanations

    quantifiable metrics or rates

    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
    æĪĸå¤ļ个
    -0.07
    uxt
    -0.07
    azer
    -0.07
    è¶ĬæĿ¥è¶Ĭå¤ļ
    -0.07
    iculo
    -0.07
    è¶Ĭå¤ļ
    -0.07
    bai
    -0.07
     whose
    -0.06
    ()._
    -0.06
    以å¤ĸ
    -0.06
    POSITIVE LOGITS
    åĪĨåĪ«ä¸º
    0.10
    åĪĨå¸ĥå¦Ĥä¸ĭ
    0.09
     ÅŁÃ¶
    0.09
    ä¸Ĭ大
    0.08
    åIJĦ家
    0.08
    åIJĦé¡¹çĽ®
    0.08
    åĪĨåĪ«æĺ¯
    0.08
    åIJĦ项任åĬ¡
    0.08
    对åIJĦç§į
    0.08
    ért
    0.08
    Activations Density 0.101%

    No Known Activations