© 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. 9595
    Prev
    Next
    INDEX
    Explanations

    technical information retrieval

    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
    åħ¼æĢ»ç»ıçIJĨ
    -0.08
    æĦıçļĦ
    -0.08
    اÙĦÙĬØ©
    -0.08
    alth
    -0.08
    heber
    -0.08
    oyer
    -0.07
    ÐĴÐĶ
    -0.07
    anness
    -0.07
    ORIZED
    -0.07
    wart
    -0.07
    POSITIVE LOGITS
    Ĩ
    0.07
    .AI
    0.07
    å¤ļç¯ĩ
    0.06
    ritz
    0.06
    tof
    0.06
    itz
    0.06
    è¦ģåĬłå¤§
    0.06
    ãĤ«ãĥĨãĤ´ãĥª
    0.06
    羸
    0.06
    à¦ļিত
    0.06
    Activations Density 0.004%

    No Known Activations