© 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. 32457
    Prev
    Next
    INDEX
    Explanations

    click, $, angle, Servlet, Hansen Brothers, brakes

    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
    egas
    -0.07
    epad
    -0.07
    ôm
    -0.06
    omp
    -0.06
    abu
    -0.06
    abas
    -0.06
    士æŀĹ
    -0.06
    úl
    -0.06
    aoke
    -0.06
    สม
    -0.06
    POSITIVE LOGITS
    ingly
    0.08
    #__
    0.07
    endr
    0.07
    ï¾ŀ
    0.07
    _gateway
    0.06
    伶
    0.06
    aland
    0.06
    PosY
    0.06
    áĢ¾
    0.06
     plafond
    0.06
    Activations Density 0.096%

    No Known Activations