© 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. 11552
    Prev
    Next
    INDEX
    Explanations

    Carvalho Chehab

    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
     Osten
    -0.07
     discretion
    -0.07
    ¾
    -0.07
    é£İéĻ©åĴĮ
    -0.07
    çļĦä¸ľè¥¿
    -0.06
    ä¸ĢäºĮ
    -0.06
    离æķ£
    -0.06
    contra
    -0.06
     pitches
    -0.06
    æģIJ
    -0.06
    POSITIVE LOGITS
     Nazar
    0.07
    ×IJ×ķת
    0.07
    模
    0.07
    omot
    0.07
    ÙİÙĨÙİÙij
    0.06
     etap
    0.06
     depart
    0.06
    çĤĴ
    0.06
    irem
    0.06
    ño
    0.06
    Activations Density 0.004%

    No Known Activations