© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 18022
    Prev
    Next
    INDEX
    Explanations

    concepts and lists

    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
    æŶéĻIJ
    -0.08
    erber
    -0.07
    æĬ¥éħ¬
    -0.07
    éħ
    -0.07
     thác
    -0.07
    erder
    -0.06
    æµģ
    -0.06
    otch
    -0.06
    çij°
    -0.06
    èĩªå·±åĸľæ¬¢çļĦ
    -0.06
    POSITIVE LOGITS
    à¸ļà¹īาà¸ĩ
    0.09
     chac
    0.07
    åºĶçĶ¨åľ¨
    0.07
    iddel
    0.07
    UNUSED
    0.07
    aje
    0.07
    اظ
    0.07
    formatted
    0.07
    fri
    0.07
    ׾×ķ
    0.06
    Activations Density 0.017%

    No Known Activations