© 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. 48615
    Prev
    Next
    INDEX
    Explanations

    `toString` 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
    æľīä»·åĢ¼çļĦ
    -0.08
    smith
    -0.08
    rieve
    -0.07
    éné
    -0.07
    ties
    -0.07
    æľī
    -0.07
     volna
    -0.07
    irk
    -0.07
    elling
    -0.07
    areth
    -0.07
    POSITIVE LOGITS
     ê´Ģ볨íķľ
    0.09
    éĤ£åı¥è¯Ŀ
    0.09
    pike
    0.09
    ÑħодÑĥ
    0.08
     ê´Ģ볨íķĺìŬ
    0.08
    ÑĪний
    0.07
    owing
    0.07
    ../
    0.07
    ocities
    0.07
    quirrel
    0.07
    Activations Density 0.001%

    No Known Activations