© 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. 19585
    Prev
    Next
    INDEX
    Explanations

    part of conversation

    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
    åĤį
    -0.06
    å½Ĵæł¹
    -0.06
    åĨįæĹł
    -0.06
    æĪijä»İ
    -0.06
    çªģ
    -0.06
    aley
    -0.06
     TZ
    -0.06
    åħļåĴĮ人æ°ij
    -0.06
    ãģªãģıãģªãģ£ãģŁ
    -0.06
    _CUSTOM
    -0.06
    POSITIVE LOGITS
    æļĤ
    0.18
    æļĤæŶ
    0.17
    åĪĿæŃ¥
    0.17
    æļĤæľª
    0.16
    æļ«
    0.15
    æļĤæŶçļĦ
    0.15
     preliminary
    0.15
    æļĤæĹ¶æ²¡æľī
    0.14
    æļĤç¼ĵ
    0.14
    æļĤè¡Į
    0.14
    Activations Density 0.389%

    No Known Activations