© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 47746
    Prev
    Next
    INDEX
    Explanations

    relative to English update

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å°¤åħ¶
    -0.08
    ,...↵
    -0.07
    ,...↵↵
    -0.07
    欢ä¹IJ
    -0.07
    ãģ¾ãģ¨
    -0.07
    æŃª
    -0.06
    尤为
    -0.06
    гоÑĤов
    -0.06
    çĹ£
    -0.06
    管çIJĨåĴĮ
    -0.06
    POSITIVE LOGITS
    çļĦ羣å®ŀæĢ§
    0.10
    egl
    0.10
    åĽłä¸ºä»ĸ们
    0.09
    terr
    0.09
    ложение
    0.09
    ould
    0.09
    好çľĭçļĦ
    0.09
    avar
    0.09
    etheless
    0.09
    sWith
    0.09
    Activations Density 1.418%

    No Known Activations