© 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. 18668
    Prev
    Next
    INDEX
    Explanations

    Temple University, Health, Beth

    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
    æ¯Ľæ³½
    -0.08
    å°±æĺ¯åĽłä¸º
    -0.08
    å¹²èĦĨ
    -0.08
     cap
    -0.08
     Shields
    -0.08
    æİĩ
    -0.08
    æ®Ĥ
    -0.08
     Ze
    -0.08
    ä¸ĩä¸Ģ
    -0.08
    xdd
    -0.08
    POSITIVE LOGITS
    媳å¦ĩ
    0.11
    æľīæĿ¡ä»¶çļĦ
    0.10
    _sb
    0.09
    ç¢Į
    0.09
     jä
    0.09
    èĥ«
    0.09
     wig
    0.09
    -born
    0.09
    ella
    0.08
    .sb
    0.08
    Activations Density 0.003%

    No Known Activations