© 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. 32039
    Prev
    Next
    INDEX
    Explanations

    past participles and 'by'

    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
     sequer
    -0.07
    stry
    -0.07
    鼶åħ«
    -0.07
    æīĢå¤ĦçļĦ
    -0.07
    žno
    -0.07
    æīĢ使çĶ¨çļĦ
    -0.07
    irme
    -0.07
    ppo
    -0.07
    klub
    -0.07
    ensa
    -0.07
    POSITIVE LOGITS
     تÙĪسط
    0.12
     by
    0.12
     нами
    0.11
     bợi
    0.10
     мной
    0.09
     oleh
    0.09
     вами
    0.09
    /generated
    0.09
    by
    0.09
    à¹Ĥà¸Ķย
    0.09
    Activations Density 0.423%

    No Known Activations