© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9325
    Prev
    Next
    INDEX
    Explanations

    next button, text, icon, method, page, div

    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
    ensi
    -0.09
    евиÑĩ
    -0.09
    åħ¥èĤ¡
    -0.09
    æľīè¿ĩ
    -0.08
    ANNEL
    -0.08
     neglig
    -0.08
    æĺ§
    -0.08
    延ç»Ń
    -0.08
    @m
    -0.08
    æ´¼
    -0.08
    POSITIVE LOGITS
    ç¢ĩ
    0.10
    agate
    0.09
    éļ½
    0.09
    çļĦå¿ĥçIJĨ
    0.09
    ãĤį
    0.09
    ä¸įåłª
    0.08
     ÙĪعÙĨ
    0.08
    èij«
    0.08
    æĪijå¾Ī
    0.08
    èĪĴ
    0.08
    Activations Density 0.036%

    No Known Activations