© 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. 16595
    Prev
    Next
    INDEX
    Explanations

    size and dimensions

    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
    èĩªå·±çļĦè¡Į为
    -0.07
    çļĦèĩªå·±
    -0.07
    aint
    -0.07
    åIJ«éĩıçļĦ
    -0.07
    anzi
    -0.06
    åıªæľīä¸Ģ次
    -0.06
    çİĩçļĦ
    -0.06
    éĺĸ
    -0.06
    çĤ¯
    -0.06
    ased
    -0.06
    POSITIVE LOGITS
     длиной
    0.09
     sizes
    0.08
     size
    0.08
     ÑĢазмеÑĢом
    0.08
     whose
    0.08
    æĸĩ件大å°ı
    0.08
     ÑĢазмеÑĢÑĭ
    0.08
    astia
    0.08
    OOT
    0.08
    ele
    0.08
    Activations Density 0.042%

    No Known Activations