© 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. 9782
    Prev
    Next
    INDEX
    Explanations

    SELECT, .NET, Manager, heavy, thunderstorms, calculations, CORE

    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
    RIX
    -0.07
    cito
    -0.07
    ~~~~~~~~
    -0.07
    åıij表æŶéĹ´
    -0.06
    yen
    -0.06
     inz
    -0.06
    ÑĢино
    -0.06
    rox
    -0.06
    QRST
    -0.06
    åħĭåĬĽ
    -0.06
    POSITIVE LOGITS
    itch
    0.07
    çĭ¬
    0.07
    dy
    0.07
    å±ŀäºİ
    0.07
    è§Ĥ
    0.07
    驾
    0.07
    atap
    0.07
    ylie
    0.07
    aiser
    0.07
    æĿĢ
    0.07
    Activations Density 0.082%

    No Known Activations