© 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. 12288
    Prev
    Next
    INDEX
    Explanations

    mortal sins, raster layers, dynamic cell, global variable

    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
    èĢĮä¸įæĺ¯
    -0.08
    ìĿ´ìŀIJ
    -0.07
    æĸ¯åį¡
    -0.07
    éĻĦè¿ijæľī
    -0.07
    dux
    -0.07
    åĴĮæĻºæħ§
    -0.07
    untu
    -0.06
    aza
    -0.06
     instead
    -0.06
    inkin
    -0.06
    POSITIVE LOGITS
     alike
    0.11
    ä¹ĭåĪĨ
    0.10
     gleicher
    0.10
     respectively
    0.09
     ê·¸ë¦¬ê³ł
    0.09
    åĪĨåĪ«
    0.09
    ãģĿãĤĮãģŀãĤĮ
    0.08
    ãģ¨ãģĦãģ£ãģŁ
    0.08
    åĨįåĪ°
    0.08
    ãģĿãģĹãģ¦
    0.08
    Activations Density 0.225%

    No Known Activations