© 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. 56723
    Prev
    Next
    INDEX
    Explanations

    protects from

    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
     dÃłnh
    -0.10
    ailing
    -0.10
    èĥ½å¾ĹåĪ°
    -0.10
     bezpieczeÅĦst
    -0.10
    icast
    -0.10
    æĪijçļĦå¿ĥ
    -0.09
    è²Ĥ
    -0.09
    ä¿ĿçķĻ
    -0.09
    quist
    -0.09
     dend
    -0.09
    POSITIVE LOGITS
    æĿ¥èĩª
    0.11
    ä¾Ĩèĩª
    0.10
    åīįæīĢ
    0.09
    åIJĦç§į
    0.09
    æĮļ
    0.08
    å¤ĸçķĮ
    0.08
    à¸ł
    0.08
    ä»»ä½ķå½¢å¼ı
    0.08
    çİĩ为
    0.08
     various
    0.08
    Activations Density 0.070%

    No Known Activations