© 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. 16579
    Prev
    Next
    INDEX
    Explanations

    call, DNA, wells, books, thread, vessels, banks

    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
    alth
    -0.07
     nowhere
    -0.07
    çĦī
    -0.06
    TA
    -0.06
     always
    -0.06
    дени
    -0.06
    ta
    -0.06
    erate
    -0.06
    æīİ
    -0.06
    +
    -0.06
    POSITIVE LOGITS
    æĺ¯ä¸Ģ项
    0.09
    使ä¹ĭ
    0.08
    çļĦæĸ¹æ³ķåĴĮ
    0.08
     меÑĤодами
    0.08
    AndGet
    0.08
    çļĦæĸ¹æ³ķæĺ¯
    0.08
     mithilfe
    0.08
    çļĦè¿ĩç¨ĭä¸Ń
    0.08
     dilakukan
    0.08
     Apel
    0.08
    Activations Density 0.798%

    No Known Activations