© 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. 28222
    Prev
    Next
    INDEX
    Explanations

    memory allocation, variables, and code snippets

    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
    inov
    -0.07
    apy
    -0.07
    кÑĥлÑĮ
    -0.07
    ezen
    -0.07
    :?
    -0.06
    -sama
    -0.06
    FSIZE
    -0.06
    ibaldi
    -0.06
    åIJİ天
    -0.06
    лÑİ
    -0.06
    POSITIVE LOGITS
    ivers
    0.07
    биÑĤ
    0.07
    äºĨå¹¾
    0.07
    atted
    0.06
    祺
    0.06
    otros
    0.06
     xsi
    0.06
    odin
    0.06
    ickle
    0.06
    åľ
    0.06
    Activations Density 0.015%

    No Known Activations