© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 10608
    Prev
    Next
    INDEX
    Explanations

    (s) suffix

    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
    artal
    -0.07
    Õ¡Õ¿
    -0.07
    ÑĢони
    -0.07
    à¸ľà¸¥
    -0.07
    gara
    -0.07
    luk
    -0.06
    æľīä¸įå°ij
    -0.06
    αιο
    -0.06
    atform
    -0.06
    fors
    -0.06
    POSITIVE LOGITS
    ruh
    0.08
    oth
    0.08
    å¾·åįİ
    0.07
    uture
    0.07
    Ä«
    0.07
    alore
    0.07
    ãģ«ãĤĪãģ£ãģ¦ãģ¯
    0.07
    unch
    0.07
    翼翼
    0.07
    enn
    0.07
    Activations Density 0.017%

    No Known Activations