© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20959
    Prev
    Next
    INDEX
    Explanations

    over the years

    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
    ä¸ĢæĹı
    -0.11
    éģ½
    -0.11
    æĸ°æĹ¶ä»£
    -0.11
    å½ĵæŶ
    -0.10
    ä»Ĭ天çļĦ
    -0.09
    åħ¨ç¤¾ä¼ļ
    -0.09
    å½ĵæŶçļĦ
    -0.09
    ãģĦãģ¾
    -0.09
    为é¦ĸçļĦ
    -0.09
    éĻ¤æѤä¹ĭå¤ĸ
    -0.09
    POSITIVE LOGITS
    æľīä¸įå°ij
    0.10
    åIJĦå¼ı
    0.09
    lass
    0.09
    æŃ·
    0.08
    -release
    0.08
    ãģĨãģ¡ãģ«
    0.08
     rele
    0.08
    åİĨ
    0.08
    liest
    0.08
    åIJIJ
    0.08
    Activations Density 0.012%

    No Known Activations