© 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. 9535
    Prev
    Next
    INDEX
    Explanations

    items ending in -ers, -ans, or words like albums, crystals, maps, agents

    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
    à·ıà·Ģ
    -0.07
    åįĬåĬŁ
    -0.07
    æŶ任
    -0.07
    elum
    -0.07
    åģ¥åĦ¿
    -0.07
    ãģłãģĭãĤīãģĵãģĿ
    -0.07
    å®Ŀåīij
    -0.07
    erland
    -0.07
    fter
    -0.07
    sville
    -0.07
    POSITIVE LOGITS
    çĬ¶
    0.07
    æħ°
    0.06
    è¿Ļç§įä¸ľè¥¿
    0.06
    inna
    0.06
    人éĢł
    0.06
    arie
    0.06
    æ¯Ļ
    0.06
    人类
    0.06
    é©°
    0.06
    ious
    0.06
    Activations Density 0.217%

    No Known Activations