© 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. 37941
    Prev
    Next
    INDEX
    Explanations

    designed to be

    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
    æĴ¥
    -0.09
    æĥ³çĿĢ
    -0.09
    dess
    -0.09
    æĹĹå¸ľ
    -0.09
    ä¹Łå¸ĮæľĽ
    -0.09
    äº²çľ¼
    -0.09
     diá»ħn
    -0.09
    æĭ¨
    -0.09
    xls
    -0.09
    ä¸įæĺİ
    -0.09
    POSITIVE LOGITS
    æĬĬä½ł
    0.09
    lider
    0.09
     nor
    0.08
    è¦ģæĬĬ
    0.08
    ALLY
    0.08
    utes
    0.08
    -strong
    0.08
    ubby
    0.08
    趣åij³
    0.08
     to
    0.08
    Activations Density 0.045%

    No Known Activations