© 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. 31675
    Prev
    Next
    INDEX
    Explanations

    mechanical linkages and levers

    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
    patches
    -0.08
     Patch
    -0.08
    å¥Ī
    -0.08
     haze
    -0.08
    èĥ½è§ģ度
    -0.08
    æŃ¢æŃ¥
    -0.07
     patch
    -0.07
    usin
    -0.07
    ligen
    -0.07
    Vien
    -0.07
    POSITIVE LOGITS
    æĶ¯çĤ¹
    0.08
    .utility
    0.08
     arm
    0.07
    è°ĥèĬĤ
    0.07
    è¿IJ
    0.07
    ìĿµ
    0.07
    æĬĺ
    0.07
    .yahoo
    0.07
    çľģåĬĽ
    0.07
    é©
    0.07
    Activations Density 0.002%

    No Known Activations