© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 635
    Prev
    Next
    INDEX
    Explanations

    resigned from

    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
    Negative Logits
    ساÙĨ
    -0.09
    arta
    -0.08
    deles
    -0.08
    产åĵģä¸Ńå¿ĥ
    -0.07
    taÅŁ
    -0.07
    cik
    -0.07
    cker
    -0.07
    ÏĦαν
    -0.07
    illing
    -0.07
    ","",
    -0.07
    POSITIVE LOGITS
    hea
    0.06
    _syntax
    0.06
    æ»¡åľ°
    0.06
    he
    0.06
    sur
    0.06
    ẻ
    0.06
    usen
    0.06
    ä½Ĩä¸įéĻIJäºİ
    0.06
    رÛĮ
    0.06
    itter
    0.05
    Activations Density 0.152%

    No Known Activations