© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 57108
    Prev
    Next
    INDEX
    Explanations

    arithmetic questions

    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
    arr
    -0.08
    erei
    -0.07
    ãģ¿ãģŁãģĦ
    -0.07
    _WRAPPER
    -0.07
    çķĻå®Ī
    -0.07
     Kantor
    -0.06
    æľĢåĢ¼å¾Ĺ
    -0.06
    å¼¥
    -0.06
    izz
    -0.06
    -boot
    -0.06
    POSITIVE LOGITS
    aing
    0.08
    ugins
    0.07
    满
    0.07
    lements
    0.07
    udi
    0.07
    eda
    0.07
    vnÃŃ
    0.07
    ometrics
    0.07
    é»ĺé»ĺçļĦ
    0.07
    odem
    0.07
    Activations Density 0.014%

    No Known Activations