© 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. 19271
    Prev
    Next
    INDEX
    Explanations

    J.ax

    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
    åºĶå½ĵä¾Ŀçħ§
    -0.07
    =u
    -0.07
    ctal
    -0.06
    ontra
    -0.06
    ery
    -0.06
     “[
    -0.06
    acto
    -0.06
    é¡¿
    -0.06
    romium
    -0.06
    篡
    -0.06
    POSITIVE LOGITS
    unded
    0.09
    inj
    0.08
    дÑĥк
    0.08
    CHE
    0.08
    ндÑĸ
    0.07
    unj
    0.07
    请å°Ĩ
    0.07
    ubs
    0.07
    ience
    0.07
    otch
    0.07
    Activations Density 0.001%

    No Known Activations