© 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. 25643
    Prev
    Next
    INDEX
    Explanations

    contents and headings

    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
    leigh
    -0.09
    çļĦä¸Ģ线
    -0.07
    æ±Ģ
    -0.07
    olygon
    -0.07
    .accept
    -0.06
    parameters
    -0.06
    岸
    -0.06
    uman
    -0.06
    æĶ¾åľ¨ç¬¬ä¸Ģä½į
    -0.06
    utherland
    -0.06
    POSITIVE LOGITS
    ç´¢å¼ķ
    0.10
     contents
    0.09
    表åĴĮ
    0.08
     headings
    0.08
    çļĦåĪĨ
    0.08
    ÚĨÙĩ
    0.08
    åħ¨ä¹¦
    0.08
    verzeichnis
    0.08
    ìĪľ
    0.08
    übers
    0.08
    Activations Density 0.075%

    No Known Activations