© 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. 26898
    Prev
    Next
    INDEX
    Explanations

    contact us or support

    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
    æ·±åĬłå·¥
    -0.09
    .exchange
    -0.09
    urn
    -0.09
    ÐľÐŀ
    -0.09
    евиÑĩ
    -0.09
    楼æĪ¿
    -0.09
    ĶåĽŀ
    -0.09
    è·ĥ
    -0.08
    èµ°å»Ĭ
    -0.08
    -types
    -0.08
    POSITIVE LOGITS
    å¿Ĵ
    0.09
    -overlay
    0.09
    说èĩªå·±
    0.09
    ä¸ĸçķĮæĿ¯
    0.09
    åı¯ä»¥è¯´
    0.08
     terme
    0.08
    assen
    0.08
    undi
    0.08
    CAPE
    0.08
    æĹłçĸij
    0.08
    Activations Density 0.003%

    No Known Activations