© 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. 43123
    Prev
    Next
    INDEX
    Explanations

    Swedish IRC or chat messages

    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
    FIX
    -0.06
    åľ¨æĹ¥å¸¸
    -0.06
    ,
    -0.06
     throughout
    -0.06
     hosting
    -0.06
    ogram
    -0.06
    èĩªåı¤ä»¥æĿ¥
    -0.06
    asy
    -0.06
    åĽºå®ļçļĦ
    -0.06
     regulating
    -0.06
    POSITIVE LOGITS
    åĽĽéĿ¢åħ«æĸ¹
    0.10
    åIJĮæĹ¶ä¹Łè¦ģ
    0.09
    onnal
    0.08
    æĮĿ
    0.08
    并åIJĮæŶ
    0.08
    resa
    0.08
    queued
    0.08
    ystems
    0.08
    OrUpdate
    0.08
    æĸ°æŃĮ
    0.08
    Activations Density 0.001%

    No Known Activations