© 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. 39946
    Prev
    Next
    INDEX
    Explanations

    (a) option letters

    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
    ä¼łçļĦ
    -0.10
     "**
    -0.09
    çīĪæĿĥå½ĴåİŁä½ľèĢħ
    -0.09
    ecs
    -0.08
    evat
    -0.08
    ä¸įè´¥
    -0.08
     <<-
    -0.08
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    -0.08
    æĬĺä¸į
    -0.08
    abia
    -0.07
    POSITIVE LOGITS
    ï¸ı
    0.10
    ãĢģ
    0.07
    ï¼ļ
    0.07
    ãĢĢ
    0.07
    hell
    0.06
    ìĤ¬ìĿ¸
    0.06
    ï¼İ
    0.06
    жа
    0.06
    ï¼ļ%
    0.06
    âĢ
    0.06
    Activations Density 0.009%

    No Known Activations