© 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. 4029
    Prev
    Next
    INDEX
    Explanations

    golf ball sports

    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
     pairwise
    -0.08
    迷宫
    -0.07
    æĮĸçŁ¿
    -0.07
     branching
    -0.07
    veau
    -0.07
    è¸ıæŃ¥
    -0.06
    æīĭèĦļ
    -0.06
    æī¶æ¢¯
    -0.06
    olest
    -0.06
     labyrinth
    -0.06
    POSITIVE LOGITS
    å°ĨçIJĥ
    0.09
    å°Ħç¨ĭ
    0.09
    -ball
    0.09
     rico
    0.09
    å¨ģåĬĽ
    0.08
    çIJĥçļĦ
    0.08
    è¿ľè¿ij
    0.08
    ç·´ç¿Ĵ
    0.08
    <|box_end|>
    0.08
    轨迹
    0.08
    Activations Density 0.136%

    No Known Activations