© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39394
    Prev
    Next
    INDEX
    Explanations

    large mediastinal tumorBritish womenaspects of

    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
    çľ¼çľĭ
    -0.09
    et
    -0.07
    amas
    -0.07
    imb
    -0.07
     Gran
    -0.07
    orb
    -0.07
    others
    -0.07
    amate
    -0.06
    amai
    -0.06
    æİĮ声
    -0.06
    POSITIVE LOGITS
    çĽ¸ä¼¼æĸĩçĮ®
    0.08
    ä¹ĭçªĹ
    0.08
    缸è¾ħ缸æĪIJ
    0.08
    >[]
    0.07
    à§Ģয়
    0.07
    ylie
    0.07
     skype
    0.07
    azi
    0.07
    åIJĦç§įåIJĦæł·
    0.06
    çī¹åĪ«å£°æĺİ
    0.06
    Activations Density 0.001%

    No Known Activations