© 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. 22586
    Prev
    Next
    INDEX
    Explanations

    how to achieve something

    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
    ç¢Ĺ
    -0.10
    ä¸ĩåįĥ
    -0.09
    贪婪
    -0.09
     gÅĤówne
    -0.09
     демо
    -0.09
    å¼¼
    -0.09
    lined
    -0.09
    ÑģÑĥд
    -0.09
     ÐłÐ°
    -0.08
    ëĦĪ
    -0.08
    POSITIVE LOGITS
    æķĻä½ł
    0.11
    æĬĢå·§
    0.10
    ç§ĺ
    0.10
    å®ŀçİ°
    0.10
    æĢİä¹Īåģļ
    0.10
    obel
    0.09
    \":{\"
    0.09
    æĹ¢èĥ½
    0.09
     accomplish
    0.09
    ç§ĺè¯Ģ
    0.09
    Activations Density 1.272%

    No Known Activations