© 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. 55093
    Prev
    Next
    INDEX
    Explanations

    did or do followed by verb

    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
    bench
    -0.10
    inki
    -0.09
    enses
    -0.09
    æ®Ħ
    -0.09
    çĸ¤
    -0.09
    头ä¸Ĭ
    -0.09
     bench
    -0.08
    çºĽ
    -0.08
    çļĦçĪ¶äº²
    -0.08
    åŁİéķĩ
    -0.08
    POSITIVE LOGITS
    ç¡®å®ŀ
    0.12
    ç¬Ļ
    0.12
    ç¡®å®ŀæĺ¯
    0.11
    çļĦç¡®æĺ¯
    0.11
    ç¡®
    0.10
    çļĦç¡®
    0.10
    æĺ¯è¦ģ
    0.09
    ä¹Łè®©
    0.09
    éĩįå¡ij
    0.09
    èĥ½å¤Łè®©
    0.09
    Activations Density 0.053%

    No Known Activations