© 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. 3839
    Prev
    Next
    INDEX
    Explanations

    physical surfaces and materials

    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
    çĭ¼çĭĪ
    -0.07
    ä½ļ
    -0.07
    ä¸Ģå¸Ĩ
    -0.07
     usher
    -0.07
    å¸ĥè¢ĭ
    -0.07
    èIJ¤çģ«
    -0.07
    赶走
    -0.07
    Bracket
    -0.06
    欢声
    -0.06
    大åĬŁ
    -0.06
    POSITIVE LOGITS
    表éĿ¢
    0.10
     surface
    0.09
    纹çIJĨ
    0.08
    表éĿ¢çļĦ
    0.08
     texture
    0.08
    ä¸īå°º
    0.08
    åħīæ»ij
    0.08
    蹦
    0.07
     superficie
    0.07
     substrate
    0.07
    Activations Density 0.160%

    No Known Activations