© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7386
    Prev
    Next
    INDEX
    Explanations

    NewPage, coding, Copyright

    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
    æŃ¤åŁºç¡Ģä¸Ĭ
    -0.11
    åĽĽä¸ªæĸ¹éĿ¢
    -0.10
    对åħ¶
    -0.09
    åIJĦ个æĸ¹éĿ¢
    -0.09
    æIJª
    -0.09
    etto
    -0.09
    ä¹Łæĺ¯å¾Ī
    -0.09
     lapse
    -0.09
    éªĦ
    -0.08
    uture
    -0.08
    POSITIVE LOGITS
    身ä½ĵ
    0.09
    -With
    0.08
    _pickle
    0.08
     ХоÑĤ
    0.08
    irim
    0.08
    ização
    0.08
    ä¸ĢåĪĩéĥ½
    0.08
    cobra
    0.08
    -TV
    0.08
    ìĸ´
    0.08
    Activations Density 0.183%

    No Known Activations