© 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. 15470
    Prev
    Next
    INDEX
    Explanations

    regex patterns

    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
    åģıå¿ĥ
    -0.07
    otrop
    -0.07
    endale
    -0.06
    åIJĥéĨĭ
    -0.06
    伶
    -0.06
    tum
    -0.06
    ä¼IJ
    -0.06
    èĤ¥
    -0.06
    èĩªçĦ¶èµĦæºIJ
    -0.06
    ocrin
    -0.06
    POSITIVE LOGITS
    .Pattern
    0.09
    (regex
    0.09
    .pattern
    0.09
     regex
    0.09
    esel
    0.08
     Regex
    0.08
    (pattern
    0.08
    Matches
    0.08
    .Matcher
    0.08
    äºĭåĬ¡æīĢ
    0.08
    Activations Density 0.100%

    No Known Activations