© 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. 36728
    Prev
    Next
    INDEX
    Explanations

    login, register, subscribe

    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
    hawks
    -0.10
    ä¸įèĪį
    -0.08
    ä¸Ģ个æĸ°çļĦ
    -0.08
    æĹĦ
    -0.08
    åIJİæŀľ
    -0.08
    ivor
    -0.08
    _proto
    -0.08
    çļĦæľĢä½³
    -0.08
     Cups
    -0.08
    æĸ°çļĦ
    -0.08
    POSITIVE LOGITS
    æīįæľī
    0.14
    æīįèĥ½å¤Ł
    0.12
    æīįçŁ¥éģĵ
    0.11
    æīįåı¯ä»¥
    0.11
    æīįèĥ½
    0.10
    éĥĦ
    0.10
    æĪIJåijĺ
    0.10
    æŃ£å¼ı
    0.10
    è¿Ļæł·æīįèĥ½
    0.10
    éĺħ读åħ¨æĸĩ
    0.10
    Activations Density 0.019%

    No Known Activations