© 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. 33285
    Prev
    Next
    INDEX
    Explanations

    let shake

    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
     thereof
    -0.12
    æį®æѤ
    -0.11
    对æѤ
    -0.10
     accordingly
    -0.10
    éļıä¹ĭ
    -0.09
     deren
    -0.08
    çĶ±æѤ
    -0.08
    ä¹Łéļıä¹ĭ
    -0.08
     ìĿ´ë¥¼
    -0.08
    缸åºĶçļĦ
    -0.08
    POSITIVE LOGITS
     ugyanis
    0.09
    对äºİä¸Ģ个
    0.08
     totiž
    0.08
    åİŁæĺ¯
    0.08
    ytu
    0.08
    olda
    0.07
    ãģĽãģ£ãģĭãģı
    0.07
    æĽ¾ç»ı说è¿ĩ
    0.07
    举个
    0.07
     firstly
    0.07
    Activations Density 0.084%

    No Known Activations