© 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. 28529
    Prev
    Next
    INDEX
    Explanations

    sunburst, oil-based, welding, gold, Windows

    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
    ocache
    -0.07
    ë¶ĢìĿĺ
    -0.06
    å¿ħ读
    -0.06
    azza
    -0.06
    å°ĨæĮīçħ§
    -0.06
    omba
    -0.06
    é¢Ĩ
    -0.06
     requested
    -0.06
    åĽł
    -0.06
    opil
    -0.06
    POSITIVE LOGITS
    主è¦ģçĶ¨äºİ
    0.10
    对äºİä¸ĢäºĽ
    0.09
    å¹¿æ³ĽçĶ¨äºİ
    0.09
    çŃīå¤ļç§įå½¢å¼ı
    0.09
    è¿Ļç§įæĸ¹å¼ı
    0.08
    两ç§įæĸ¹å¼ı
    0.08
    常çĶ¨äºİ
    0.08
    å¹¿æ³ĽåºĶçĶ¨äºİ
    0.08
    å¤ļç§įå½¢å¼ı
    0.08
    为è¾ħ
    0.08
    Activations Density 0.034%

    No Known Activations