© 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. 64812
    Prev
    Next
    INDEX
    Explanations

    .ToString() or str() conversion

    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
    åĬ¿å¤´
    -0.07
    ('/',
    -0.07
    pare
    -0.07
     sekali
    -0.07
    é«ĺä¸ĵ
    -0.07
    iny
    -0.07
    ÙĪÙĨا
    -0.06
    wig
    -0.06
    pl
    -0.06
    说å®ŀè¯Ŀ
    -0.06
    POSITIVE LOGITS
    ftime
    0.08
    æŁ¿
    0.07
     ISSN
    0.07
    (describing
    0.07
    orio
    0.07
    bject
    0.07
    tring
    0.07
    èĨ
    0.07
    çıĬçıĬ
    0.07
    aval
    0.06
    Activations Density 0.033%

    No Known Activations