© 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. 45571
    Prev
    Next
    INDEX
    Explanations

    string concatenation with comma

    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
    åŀĽ
    -0.07
    躯
    -0.06
     dos
    -0.06
    çļĦå¿ĥæĦ¿
    -0.06
    wich
    -0.06
    beck
    -0.06
     qr
    -0.06
    åĬ¨è¾Ħ
    -0.06
    legs
    -0.06
     vr
    -0.06
    POSITIVE LOGITS
    wed
    0.09
    zar
    0.08
    amba
    0.08
    chend
    0.08
     Afg
    0.08
    rita
    0.08
    ibir
    0.07
    (encoding
    0.07
    _trees
    0.07
    æ±Ĥç²¾
    0.07
    Activations Density 0.005%

    No Known Activations