© 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. 30865
    Prev
    Next
    INDEX
    Explanations

    highest, best, and top quality

    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
    æ¼ı
    -0.08
    æ¹Ķ
    -0.08
    毯
    -0.08
    åħ«å¤§
    -0.08
    èĤĮ
    -0.08
    æį®æѤ
    -0.08
    å®īçĦ¶
    -0.08
    æĻ®
    -0.08
    ä¹Ŀ大
    -0.08
    	direction
    -0.08
    POSITIVE LOGITS
    æľĢæĸ°çļĦ
    0.17
    æľĢæĸ°
    0.14
    æľĢåħĪè¿ĽçļĦ
    0.13
    æľĢ好çļĦ
    0.13
     latest
    0.13
    ä¸ĸçķĮä¸Ģæµģ
    0.13
    æľĢé«ĺçļĦ
    0.11
    è§Ħ模æľĢ大
    0.11
     utmost
    0.11
    顶å°ĸ
    0.11
    Activations Density 0.100%

    No Known Activations