© 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. 46439
    Prev
    Next
    INDEX
    Explanations

    scientific, technological, or brand names

    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
    _CHARS
    -0.07
    ä¾Ľ
    -0.07
    _SUPPORTED
    -0.07
    åıĮæĸ¹
    -0.07
    amb
    -0.06
    æīĭä¸Ń
    -0.06
    æĨĶæĤ´
    -0.06
     éduc
    -0.06
    对èĩªå·±çļĦ
    -0.06
    utr
    -0.06
    POSITIVE LOGITS
    ilos
    0.09
    yse
    0.08
    åĨ¶
    0.07
    åĨĴéĻ©
    0.07
    aland
    0.07
    zung
    0.07
    èµ·æŃ¥
    0.07
    تÙħا
    0.07
    鼶åħ«
    0.07
    LocalizedString
    0.07
    Activations Density 0.015%

    No Known Activations