© 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. 15593
    Prev
    Next
    INDEX
    Explanations

    numbers following sequences

    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
     seur
    -0.06
    Ø·ÙĨ
    -0.06
    (
    -0.06
    漫漫
    -0.05
    è¹Ĥ
    -0.05
    )
    -0.05
    åĸĺæģ¯
    -0.05
    æĤ²æ¬¢
    -0.05
     COPYING
    -0.05
    loon
    -0.05
    POSITIVE LOGITS
     Caucus
    0.08
    erti
    0.08
    à¸IJ
    0.08
    æ³¢ç½Ĺ
    0.08
    åĩºä¸į
    0.08
    tru
    0.08
    bject
    0.08
     пÑĢокомменÑĤи
    0.08
    ematik
    0.08
    irut
    0.08
    Activations Density 0.023%

    No Known Activations