© 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. 60591
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas with numbers

    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
    erts
    -0.07
    åı¯ä¾Ŀ
    -0.07
     Lassen
    -0.07
    (encoding
    -0.07
    SK
    -0.06
    engen
    -0.06
    åĹľå¥½
    -0.06
    venus
    -0.06
    rimp
    -0.06
    nist
    -0.06
    POSITIVE LOGITS
    onica
    0.07
    åIJĮæŃ¥
    0.07
    å¾·æĭī
    0.07
    ัà¸ĩ
    0.07
    hort
    0.07
    ç¦ģ
    0.07
    æ¼Ĥ
    0.07
    egas
    0.07
    解éĻ¤
    0.07
    à¹īา
    0.06
    Activations Density 0.002%

    No Known Activations