© 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. 42905
    Prev
    Next
    INDEX
    Explanations

    relate, correlate, link, contrast

    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
    à®Łà¯įà®ļ
    -0.07
     ÙĪعÙĦÙī
    -0.07
    æĸĩç«łäºĨ
    -0.07
    à§ģম
    -0.07
    μη
    -0.06
     dac
    -0.06
     Iglesias
    -0.06
    à¹īาà¸Ļ
    -0.06
    ForResource
    -0.06
     Either
    -0.06
    POSITIVE LOGITS
    à¹Ģà¸Ĥà¹īาà¸ģัà¸ļ
    0.09
    åħ¶ä¸İ
    0.09
    è¿Ļä¸İ
    0.09
    å®ĥä¸İ
    0.09
    ä¼ļä¸İ
    0.09
    åĪĨæŀIJä¸İ
    0.09
    åı¯èĥ½ä¸İ
    0.08
    çIJĨ论ä¸İ
    0.08
    åħ¬åı¸ä¸İ
    0.08
     disparate
    0.08
    Activations Density 0.133%

    No Known Activations