© 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. 47442
    Prev
    Next
    INDEX
    Explanations

    US court appeals documents

    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
    çĻ»å½ķåIJİ
    -0.08
    ова
    -0.07
    太好
    -0.07
    unday
    -0.07
     spons
    -0.07
    lega
    -0.07
    æľĪå¼Ģå§ĭ
    -0.07
    ä¸ĩå²ģ
    -0.07
    lose
    -0.07
    imax
    -0.07
    POSITIVE LOGITS
    å¾Ĺä¸Ĭ
    0.07
    俱ä¹IJéĥ¨
    0.07
    éĺ¿æĭī伯
    0.06
    opard
    0.06
    è·ĥè·ĥ欲è¯ķ
    0.06
    erve
    0.06
    oto
    0.06
    ¯
    0.06
    äºĶé¢ľåħŃèī²çļĦ
    0.06
    ¹
    0.06
    Activations Density 0.106%

    No Known Activations