© 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. 48420
    Prev
    Next
    INDEX
    Explanations

    turns out

    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
    éļıåį³
    -0.12
    éļıåIJİ
    -0.11
    åĿļæĮģ以
    -0.11
    æģ¤
    -0.10
    ä¸ĢæŶ
    -0.09
    å·´å·´
    -0.09
     Manson
    -0.09
    æĺİçŁ¥
    -0.09
    å¨ĺ
    -0.09
    est
    -0.09
    POSITIVE LOGITS
    æĺ¯è¦ģ
    0.08
    гаÑĢ
    0.08
    skirts
    0.08
    owe
    0.08
     Lancaster
    0.08
    æľī两ç§į
    0.08
     Dop
    0.08
     needing
    0.08
    çĦ¶æĺ¯
    0.07
    æĺ¯æľī
    0.07
    Activations Density 0.005%

    No Known Activations