© 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. 34550
    Prev
    Next
    INDEX
    Explanations

    Bitcoin, offers, requests, invention, blog

    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
    èĤĥ
    -0.13
    帽
    -0.09
    æĮ¤
    -0.09
    çľ¼ä¸ĭ
    -0.09
    urge
    -0.09
    (prod
    -0.09
    digital
    -0.08
    æĸ°å±ĢéĿ¢
    -0.08
    isse
    -0.08
     sorter
    -0.08
    POSITIVE LOGITS
     BTC
    0.09
    åݨå¸Ī
    0.09
    ä¹IJæĦı
    0.09
    çļĦä¸ĢåĪĩ
    0.09
    ä¸ĢåĪĩéĥ½æĺ¯
    0.09
    æ²ı
    0.08
    ä¿ı
    0.08
    个æĢ§åĮĸ
    0.08
    æĸ¹æĸ¹éĿ¢éĿ¢
    0.08
     Va
    0.08
    Activations Density 0.029%

    No Known Activations