© 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. 3358
    Prev
    Next
    INDEX
    Explanations

    May, death, or wishes

    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
    绸
    -0.08
    åĵ©
    -0.08
    æĶ¶åĪ°äºĨ
    -0.08
    离
    -0.08
    aments
    -0.08
     clos
    -0.08
    çļĦæĥħå½¢
    -0.08
     Ventura
    -0.08
    ä¸ĸçķĮè§Ĥ
    -0.08
    col
    -0.08
    POSITIVE LOGITS
    æĦ¿
    0.11
    æĦīå¿«
    0.10
    isse
    0.10
     Hydra
    0.10
     favor
    0.09
    cej
    0.09
    ç¥Ŀ
    0.09
     favour
    0.09
    尽快
    0.09
    主ä½ĵ
    0.09
    Activations Density 0.038%

    No Known Activations