© 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. 9829
    Prev
    Next
    INDEX
    Explanations

    et al. citation

    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
     ($(
    -0.07
    uj
    -0.07
    æį¨
    -0.06
    ä¸Ģæ°Ķ
    -0.06
    ">%
    -0.06
    å±ķå¼Ģåħ¨æĸĩ
    -0.06
    äºİ人
    -0.06
    ostream
    -0.06
    .createElement
    -0.06
    ">*</
    -0.06
    POSITIVE LOGITS
    âĢ
    0.08
    alian
    0.07
    ÌĢ
    0.07
    reece
    0.07
    achu
    0.07
    ached
    0.06
    abbr
    0.06
    emand
    0.06
    ยà¸Ļ
    0.06
    ़
    0.06
    Activations Density 1.445%

    No Known Activations