© 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. 27076
    Prev
    Next
    INDEX
    Explanations

    RRSP/RRIF savings plans

    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
    åIJł
    -0.10
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.09
    æĸ¥
    -0.09
    ä¹Łä¸įçŁ¥éģĵ
    -0.08
    æĭŃ
    -0.08
    票
    -0.08
    åĽŁ
    -0.08
    teil
    -0.08
    æĪijä»¬ä¹Ł
    -0.08
    ä»·
    -0.08
    POSITIVE LOGITS
     Rider
    0.09
    侨
    0.09
    å½ĵå¹´
    0.08
    å¯Ŀ室
    0.08
     kits
    0.08
    大æĪ·
    0.08
    åѦåłĤ
    0.08
    åĿį
    0.08
    æ°ijæĶ¿
    0.08
     Sesso
    0.08
    Activations Density 0.186%

    No Known Activations