© 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. 27355
    Prev
    Next
    INDEX
    Explanations

    string concatenation

    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
    ak
    -0.06
    ear
    -0.06
    æį·
    -0.06
    2
    -0.06
    way
    -0.06
     Hub
    -0.06
    aki
    -0.06
    راج
    -0.06
    weed
    -0.06
     dram
    -0.06
    POSITIVE LOGITS
     concaten
    0.10
    concat
    0.10
     concatenated
    0.10
    Concat
    0.09
    ä¾Ŀ次为
    0.09
    åĽĽä¸ªåŃĹ
    0.09
    _concat
    0.09
    uffix
    0.09
     Concat
    0.09
    Prefix
    0.09
    Activations Density 0.013%

    No Known Activations