© 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. 32642
    Prev
    Next
    INDEX
    Explanations

    smooth manifolds

    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
    marsh
    -0.08
    Å«k
    -0.08
    ç³ĸæµĨ
    -0.08
     barley
    -0.08
    è¿ŀçݯ
    -0.08
    å®Īä¿¡
    -0.08
    å·¢
    -0.07
    麦èĬ½
    -0.07
    UMMY
    -0.07
     Muda
    -0.07
    POSITIVE LOGITS
     equipped
    0.09
     surfaces
    0.09
     curvature
    0.09
     smooth
    0.08
    smooth
    0.08
    åħīæ»ij
    0.08
    Smooth
    0.08
    åľ°åĽ¾
    0.08
    olie
    0.07
    å´İå²ĸ
    0.07
    Activations Density 0.060%

    No Known Activations