© 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. 60338
    Prev
    Next
    INDEX
    Explanations

    Legolas, Iida, Spike, Chopper, Piccolo

    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
    åħļå§Ķå§Ķåijĺ
    -0.06
    ä¸İçݯå¢ĥ
    -0.06
    åı£æ°Ķ
    -0.06
    éĺ
    -0.06
    汹汹
    -0.06
    lid
    -0.06
    ulent
    -0.06
    çİ©æĦı
    -0.06
    æĺ¯ä¸Ģé¢Ĺ
    -0.06
    éĽĩåijĺ
    -0.06
    POSITIVE LOGITS
    缸åħ³éĵ¾æİ¥
    0.08
    åįĥç§ĭ
    0.08
    anos
    0.08
    两ä¼ļ
    0.07
    ÑıÑĤи
    0.07
    ongo
    0.07
    _FIX
    0.07
    çīµ
    0.07
     Objective
    0.07
    ropri
    0.07
    Activations Density 0.065%

    No Known Activations