© 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. 25363
    Prev
    Next
    INDEX
    Explanations

    processing, mark, email, interpreters, space, oil, testing, cold

    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
    ãģ®ãģĭãĤĤãģĹãĤĮ
    -0.07
    æĭįæĭį
    -0.07
    гийн
    -0.07
    azzo
    -0.07
    çļĭ
    -0.07
     Suarez
    -0.07
    讲åĿĽ
    -0.07
     spu
    -0.07
     برگ
    -0.07
    teri
    -0.06
    POSITIVE LOGITS
    ä¹ĭçĶ¨
    0.07
     respectively
    0.07
    faits
    0.07
    èm
    0.07
     иÑħ
    0.06
     ÙħØ·
    0.06
    hazi
    0.06
     ãĢĤ
    0.06
    enan
    0.06
    å½ĵçĦ¶äºĨ
    0.06
    Activations Density 0.346%

    No Known Activations