© 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. 64453
    Prev
    Next
    INDEX
    Explanations

    concatenate strings or lists

    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
    niec
    -0.07
    -0.07
    монÑĤ
    -0.06
    عاد
    -0.06
    ÅĽ
    -0.06
    νοÏĤ
    -0.06
     ÑģÑĥÑĤок
    -0.06
    _none
    -0.06
    룬
    -0.06
    allas
    -0.06
    POSITIVE LOGITS
    enate
    0.12
    åľ¨ä¸Ģèµ·
    0.12
    åľ¨ä¸Ģèµ·çļĦ
    0.12
    èĢĮæĪIJçļĦ
    0.12
    inous
    0.11
    èĢĮæĪIJ
    0.10
    åIJĪãĤıãģĽãģŁ
    0.10
    concat
    0.09
    åĪ°ä¸Ģèµ·
    0.09
    èµ·æĿ¥çļĦ
    0.09
    Activations Density 0.012%

    No Known Activations