© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 61322
    Prev
    Next
    INDEX
    Explanations

    chief officer

    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
    éħIJ
    -0.10
    sty
    -0.09
    è¿ĩå¹´
    -0.09
    èį¤
    -0.09
    çı£
    -0.09
    æĺİçıł
    -0.09
     Feather
    -0.09
     Kendrick
    -0.09
    -League
    -0.09
    æĢ§åĴĮ
    -0.09
    POSITIVE LOGITS
    è¾Ī
    0.08
    ship
    0.08
    ums
    0.08
    ä¸ĸçķĮä¸ĬæľĢ
    0.08
    oul
    0.08
    åľ¨å¸Ĥåľºä¸Ĭ
    0.08
    åħ¨çIJĥç»ıæµİ
    0.08
     заб
    0.07
    裨
    0.07
    æĺĶæĹ¥
    0.07
    Activations Density 0.008%

    No Known Activations