© 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. 3276
    Prev
    Next
    INDEX
    Explanations

    when you

    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
    å±ĬæŶ
    -0.10
     zal
    -0.09
    å·¥ä½ľå²Ĺä½į
    -0.09
    å¼ĢåIJ¯äºĨ
    -0.09
    说ä¸įå®ļ
    -0.09
    çĥĥ
    -0.08
    кÑĥÑģ
    -0.08
    ä½ľæĸĩ
    -0.08
    bum
    -0.08
     Franklin
    -0.08
    POSITIVE LOGITS
    å°±åºĶ该
    0.10
    orsi
    0.09
    è¿Ļæł·çļĦ
    0.09
    å¾Ĺä½ı
    0.09
    ä»Ģä¹Īåı«
    0.09
    çļĦåĬ¨åĬĽ
    0.08
    æľīè¿Ļæł·çļĦ
    0.08
    å½ĵä½ł
    0.08
    客æĪ·æıIJä¾Ľ
    0.08
     ÙĬÙĥÙĪÙĨ
    0.08
    Activations Density 0.113%

    No Known Activations