© 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. 18326
    Prev
    Next
    INDEX
    Explanations

    related to measurements and construction

    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
    essin
    -0.08
    erg
    -0.08
    zial
    -0.08
    βε
    -0.08
    ÑĤок
    -0.07
    ellar
    -0.07
    gangen
    -0.07
    ׳×Ļ×ķת
    -0.07
    åĩºèµĦé¢Ŀ
    -0.07
    à¸ĺาà¸Ļ
    -0.07
    POSITIVE LOGITS
    ä½Ĩä¸įéĻIJäºİ
    0.10
    å¾Ĭ
    0.08
    ãĤ£
    0.07
    emper
    0.06
    ure
    0.06
    åģļ大
    0.06
    ุม
    0.06
    sy
    0.06
    ãģ¡
    0.06
    ablish
    0.06
    Activations Density 2.132%

    No Known Activations