© 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. 24867
    Prev
    Next
    INDEX
    Explanations

    staff reports, data, Mistresses

    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
    ä»Ģ
    -0.06
    å¼ģ
    -0.06
    _REGS
    -0.06
     tic
    -0.06
     Bradford
    -0.06
    UNC
    -0.06
    rens
    -0.06
    elts
    -0.06
    lair
    -0.06
    tick
    -0.06
    POSITIVE LOGITS
    åij¼
    0.07
    ä»ĭ
    0.07
    endr
    0.07
    мли
    0.07
    undi
    0.07
    kori
    0.07
    uu
    0.06
    baugh
    0.06
    Æ°á»Ľ
    0.06
     ÐľÐµÐ´Ð¸
    0.06
    Activations Density 0.481%

    No Known Activations