© 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. 11332
    Prev
    Next
    INDEX
    Explanations

    adverbs followed by verbs

    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
     basically
    -0.08
    ä¹°çļĦ
    -0.08
     essentially
    -0.08
    缴æİ¥è¿Ľåħ¥
    -0.08
    缴æİ¥çĶ¨
    -0.08
     readily
    -0.07
    ãĤĤãģ¨
    -0.07
    are
    -0.07
    é¦ĸåħĪæĺ¯
    -0.07
     necessarily
    -0.07
    POSITIVE LOGITS
    ly
    0.11
    (?)
    0.10
     (?)
    0.10
    ely
    0.10
    åľ°å°Ĩ
    0.10
    æĢ§åľ°
    0.10
    ently
    0.09
    mente
    0.09
    aneously
    0.09
    atively
    0.09
    Activations Density 0.206%

    No Known Activations