© 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. 27210
    Prev
    Next
    INDEX
    Explanations

    site profile

    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
    ä¹ŁæŃ£æĺ¯
    -0.09
    è´µ
    -0.09
    墨
    -0.09
    ä¸įæŃ¢
    -0.09
    ike
    -0.09
    ä¸įä»ħæĺ¯
    -0.08
    ç¿
    -0.08
    æĹ¢æľī
    -0.08
    markets
    -0.08
    æĹ¢
    -0.08
    POSITIVE LOGITS
    妲
    0.09
    æľ¬èº«çļĦ
    0.09
     Wong
    0.09
    ä¸ĬçļĦ
    0.09
     itself
    0.08
    ogne
    0.08
    çİ°æľīçļĦ
    0.08
    urgeon
    0.08
    åŁºçŁ³
    0.08
    佯
    0.08
    Activations Density 0.622%

    No Known Activations