© 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. 33594
    Prev
    Next
    INDEX
    Explanations

    metatarsal, imatinib, Romney, Carter

    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
    Whilst
    -0.09
    uto
    -0.09
    ä¸ĢåĪĩçļĦ
    -0.09
    亦æĪĸæĺ¯
    -0.08
     anyways
    -0.08
     Whilst
    -0.08
    intang
    -0.08
    为äºĨæĽ´å¥½çļĦ
    -0.08
     whilst
    -0.07
    lemen
    -0.07
    POSITIVE LOGITS
    ä¹ĭéķ¿
    0.07
    gings
    0.07
    gresql
    0.07
    è¿Ŀæ³ķåĴĮä¸įèī¯
    0.06
    çīĪçļĦ
    0.06
    tima
    0.06
    shal
    0.06
     flare
    0.06
    åĪ»çĶ»
    0.06
    ä¹ĭæĢ¥
    0.06
    Activations Density 0.493%

    No Known Activations