© 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. 24173
    Prev
    Next
    INDEX
    Explanations

    family oriented

    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
    çŃĶ主
    -0.09
     “âĢ¦
    -0.08
    çļĦå°ıç¼ĸ
    -0.08
    æĥ«
    -0.08
     (“
    -0.07
    就象
    -0.07
    æľ¬ç¯ĩ
    -0.07
     ìŀIJìĭłìĿĺ
    -0.07
    æľ¬æĸĩä¸Ń
    -0.07
    æĢĿãĤıãģļ
    -0.07
    POSITIVE LOGITS
    éĿŀ常好çļĦ
    0.10
    éĿŀ常好
    0.10
    æĪijè·Ł
    0.10
     êµīìŀ¥íŀĪ
    0.10
     somebody
    0.10
     everybody
    0.09
    éĿŀ常快
    0.09
    åĽĽäºĶ
    0.09
     very
    0.09
    å¾Ģåīįèµ°
    0.09
    Activations Density 0.640%

    No Known Activations