© 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. 58768
    Prev
    Next
    INDEX
    Explanations

    string join method calls

    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
    iol
    -0.07
    irt
    -0.07
    irit
    -0.07
    ron
    -0.07
    ï¸ı
    -0.07
    çħ§æł·
    -0.07
    åŃ¦å·¥
    -0.07
    ιν
    -0.07
    inite
    -0.06
    ullan
    -0.06
    POSITIVE LOGITS
    _ascii
    0.08
    æĪIJç«ł
    0.08
    voc
    0.07
    ToString
    0.07
     Dere
    0.07
    erÃŃa
    0.07
    egy
    0.07
    èijĨ
    0.07
    (sorted
    0.06
    าà¸Ĺี
    0.06
    Activations Density 0.001%

    No Known Activations