© 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. 29580
    Prev
    Next
    INDEX
    Explanations

    surpassed rivals winning

    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
    iskan
    -0.09
    æĶ¾è¿ĩ
    -0.08
     оÑĤкÑĥда
    -0.08
     berj
    -0.08
    âng
    -0.08
    opers
    -0.08
    akarta
    -0.08
    toral
    -0.08
    cke
    -0.08
    ä¸ĢåĽŀäºĭ
    -0.08
    POSITIVE LOGITS
    ä¸ĢçŃ¹
    0.14
     بÙĥØ«ÙĬر
    0.09
     surpassed
    0.09
    ä¸įåıĬ
    0.08
    à¹ĥà¸Ļà¸Ķà¹īาà¸Ļ
    0.08
     rivals
    0.08
     surpass
    0.08
     nhau
    0.08
    ingly
    0.08
    åľ¨æīĢæľī
    0.07
    Activations Density 0.166%

    No Known Activations