© 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. 34286
    Prev
    Next
    INDEX
    Explanations

    section, at, White, very

    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
    è¾¾æĸ¯
    -0.08
     dicon
    -0.07
    werben
    -0.07
     Panel
    -0.07
     perspectiv
    -0.07
    iefe
    -0.07
    undi
    -0.07
    ervas
    -0.06
    adeon
    -0.06
    代代
    -0.06
    POSITIVE LOGITS
    é¹ıé£ŀ
    0.07
    åı
    0.07
    ÏĥεÏīν
    0.07
    κει
    0.07
    渤
    0.07
    rogen
    0.07
    waÅĤa
    0.07
     ç§ģ
    0.06
    ui
    0.06
    çļĦ缮çļĦ
    0.06
    Activations Density 0.001%

    No Known Activations