© 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. 24743
    Prev
    Next
    INDEX
    Explanations

    MLM, frame, camera, link, server

    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
    abus
    -0.08
    avance
    -0.08
    oftware
    -0.08
    ÅĤon
    -0.08
     Habana
    -0.08
    ÙĪاÙĨ
    -0.07
    צ×ķ×¢
    -0.07
    trys
    -0.07
    illow
    -0.07
     !***
    -0.07
    POSITIVE LOGITS
    quito
    0.07
    allah
    0.06
    оÑĤо
    0.06
    ques
    0.06
    кÑĢÑĥ
    0.06
    DK
    0.05
    æķ´
    0.05
    uolo
    0.05
    usak
    0.05
    insky
    0.05
    Activations Density 0.430%

    No Known Activations