© 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. 22641
    Prev
    Next
    INDEX
    Explanations

    programming object access and methods

    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
    org
    -0.07
    ourd
    -0.07
    奥åĪ©
    -0.06
    uhr
    -0.06
    çīº
    -0.06
    éļ¶å±ŀ
    -0.06
    erne
    -0.06
    Ùıد
    -0.06
    edly
    -0.06
    thus
    -0.06
    POSITIVE LOGITS
    htable
    0.08
    empre
    0.07
    unkt
    0.07
     Pilk
    0.07
    çĤ¯
    0.07
    æĢİä¹Īæł·äºĨ
    0.07
    çĻ¾åIJį
    0.07
     Dein
    0.07
    اÙĨØ´
    0.07
    å¾·éŁ³
    0.06
    Activations Density 0.287%

    No Known Activations