© 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. 20995
    Prev
    Next
    INDEX
    Explanations

    math and physics notation

    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
    转åŀĭ
    -0.07
    åĶ¾
    -0.07
    íģIJ
    -0.07
    .hr
    -0.06
    éģĩ
    -0.06
    ÑĤÑĢа
    -0.06
    è½īåŀĭ
    -0.06
    uly
    -0.06
     strchr
    -0.06
    rimon
    -0.06
    POSITIVE LOGITS
    åĪļä¸Ģ
    0.08
    asin
    0.07
     Goth
    0.07
    å¢ŀåĬł
    0.07
    enville
    0.07
    èĥ¸æĢĢ
    0.07
    家å®Ŀ
    0.07
    emale
    0.07
    avity
    0.07
    å¿ĥåľ°
    0.07
    Activations Density 0.006%

    No Known Activations