© 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. 58462
    Prev
    Next
    INDEX
    Explanations

    greater than

    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
    anza
    -0.09
    ucch
    -0.09
    oley
    -0.07
     (--
    -0.07
    ä¸Ģè¿Ľ
    -0.07
    æĭľ
    -0.07
    contrib
    -0.06
    çĽ¸å¯¹åºĶçļĦ
    -0.06
    antry
    -0.06
    æ¯ı天éĥ½ä¼ļ
    -0.06
    POSITIVE LOGITS
    ä¸īèĢħ
    0.10
     triple
    0.09
    ä¸īè¿ŀ
    0.08
     Triple
    0.08
    iple
    0.08
    ä¸ī项
    0.08
    è¿ĻäºĽä¸ľè¥¿
    0.07
    ä¸įæ¼ı
    0.07
    idor
    0.07
    irat
    0.07
    Activations Density 0.005%

    No Known Activations