© 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. 41626
    Prev
    Next
    INDEX
    Explanations

    gift or for a guest

    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
    被称为
    -0.07
     largely
    -0.06
     Era
    -0.06
    大è§Ħ模
    -0.06
    çĶŁæŃ»
    -0.06
    大èĩ´
    -0.06
     Clear
    -0.06
     famously
    -0.05
     broadly
    -0.05
    巨大
    -0.05
    POSITIVE LOGITS
    æĪĸ个人
    0.09
    æĬķèµĦæĪĸ
    0.09
     íĺ¹ìĿĢ
    0.09
    éĥ½ä¸įä¼ļ
    0.09
    orros
    0.08
    éĥ½æľīäºĨ
    0.08
    à¸Ĥà¸Ńà¸ĩà¸Ħุà¸ĵ
    0.08
    guer
    0.08
    åıij表æĪĸ
    0.08
     wishlist
    0.08
    Activations Density 0.840%

    No Known Activations