© 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. 32017
    Prev
    Next
    INDEX
    Explanations

    natural compounds and elements

    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
    ç½¢
    -0.09
    æķ´ä½ĵ
    -0.09
    åŃ°
    -0.08
    ÙĪاÙĦ
    -0.08
    .dispatchEvent
    -0.08
    ventus
    -0.08
     scope
    -0.08
    å¦ĤæľŁ
    -0.07
    èłķ
    -0.07
    ovable
    -0.07
    POSITIVE LOGITS
    åŃĺåľ¨äºİ
    0.11
    zig
    0.09
    责任人
    0.09
     active
    0.09
    istica
    0.09
    åħ®
    0.09
    erin
    0.09
     components
    0.09
    åIJį为
    0.09
    æĪIJåĪĨ
    0.09
    Activations Density 0.254%

    No Known Activations