© 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. 31764
    Prev
    Next
    INDEX
    Explanations

    least to most

    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
     Broker
    -0.11
    ä¹Łæĺ¯å¾Ī
    -0.10
    é»İæĺİ
    -0.10
     наÑģÑĤоÑı
    -0.09
    为äºĨéģ¿åħį
    -0.09
     Bris
    -0.09
    æ¯ħ
    -0.09
    æķ´ä¸ªäºº
    -0.09
    æī¿æİ¥
    -0.09
    æ·¡æ·¡çļĦ
    -0.08
    POSITIVE LOGITS
    缸æ¯Ķä¹ĭä¸ĭ
    0.19
    ä¸įåĥı
    0.17
    åħ¶ä»ĸ
    0.14
    åħ¶ä»ĸ人
    0.13
     unlike
    0.13
     other
    0.13
    对æ¯Ķ
    0.13
    Unlike
    0.12
    ä¼łç»Ł
    0.12
    åħ¶ä»ĸåĽ½å®¶
    0.12
    Activations Density 0.210%

    No Known Activations