© 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. 50353
    Prev
    Next
    INDEX
    Explanations

    working on research and projects

    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
    å±ħé«ĺ
    -0.08
    æıIJä¾ĽæľįåĬ¡
    -0.08
    çĪ½å¿«
    -0.08
    اÙģات
    -0.08
    éģ¿éĻ©
    -0.08
    å¹´é¾Ħè¦ģæ±Ĥ
    -0.07
    尼奥
    -0.07
    ylv
    -0.07
    voz
    -0.07
    æĶ¾è¡Į
    -0.07
    POSITIVE LOGITS
    çłĶ究
    0.13
     research
    0.12
     researching
    0.12
    çłĶ究åĴĮ
    0.12
     efforts
    0.12
    æݢ索
    0.12
     nghiên
    0.11
     search
    0.10
     study
    0.10
    寻æī¾
    0.10
    Activations Density 0.814%

    No Known Activations