© 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. 42825
    Prev
    Next
    INDEX
    Explanations

    left or right forelimbs/hindlimbs

    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
    æݨæķ²
    -0.07
    æľīåı¯èĥ½æĺ¯
    -0.07
     bid
    -0.07
    æĻļ
    -0.07
    ç»Ī
    -0.07
    å¾Īåı¯èĥ½æĺ¯
    -0.07
    å¤ļå°ij次
    -0.06
    лÑĩа
    -0.06
     late
    -0.06
    åıįè¿ĩæĿ¥
    -0.06
    POSITIVE LOGITS
    enville
    0.08
    iby
    0.08
    obie
    0.08
    icur
    0.07
    izen
    0.07
    åĽºåĮĸ
    0.07
     groupName
    0.07
    anee
    0.07
    æĺ¯ä¸Ģç§į常è§ģçļĦ
    0.07
    oby
    0.07
    Activations Density 0.046%

    No Known Activations