© 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. 31233
    Prev
    Next
    INDEX
    Explanations

    introductionsmall

    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
    -0.06
     umbrella
    -0.06
     composite
    -0.06
    ě[
    -0.06
    illi
    -0.05
    ä¼ŀ
    -0.05
     $\
    -0.05
     primarily
    -0.05
     $
    -0.05
    ney
    -0.05
    POSITIVE LOGITS
    steller
    0.09
    говаÑĢи
    0.09
    èµŀè¿ĩ
    0.09
    enario
    0.08
    åħ°è¾¾
    0.08
    òi
    0.08
    ẹt
    0.08
    ÑģовеÑģÑĤ
    0.08
    ocos
    0.08
    åıĪå¤ļ
    0.08
    Activations Density 0.001%

    No Known Activations