© 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. 24256
    Prev
    Next
    INDEX
    Explanations

    state, loss, win

    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
    æħµ
    -0.08
    à¹Ģà¸Ķà¹ĩà¸Ķ
    -0.08
    æĹ¢
    -0.08
     delic
    -0.08
    ä¸įä»ħéľĢè¦ģ
    -0.07
     ÑħодÑĥ
    -0.07
    peci
    -0.07
    轻轻ä¸Ģ
    -0.07
    æĸĩæѦ
    -0.07
    hofer
    -0.07
    POSITIVE LOGITS
    æĢ»æ¯Ķ
    0.10
    çijķ
    0.09
     anyway
    0.09
    å°½åĬĽ
    0.09
    ä¸įéĶĻäºĨ
    0.08
    ä½ķåĨµ
    0.08
     valuable
    0.08
    èµ·çłģ
    0.08
     comunque
    0.08
     imperfect
    0.08
    Activations Density 0.182%

    No Known Activations