© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 798
    Prev
    Next
    INDEX
    Explanations

    to + 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
    Negative Logits
    çĦ¶æĺ¯
    -0.10
    ĵåIJį
    -0.09
    è¦ģ害
    -0.09
    å°±æĺ¯è¦ģ
    -0.09
    éĺĹ
    -0.09
    æĻĤåĢĻ
    -0.09
    ãĤīãģĦ
    -0.08
    媵
    -0.08
    表æĥħ
    -0.08
    åŁºæľ¬åİŁåĪĻ
    -0.08
    POSITIVE LOGITS
    eses
    0.12
    istes
    0.10
     quán
    0.10
    èµ·åĪ°
    0.10
    ä½ĵä¼ļåĪ°
    0.09
    ses
    0.09
    /is
    0.09
    èĪ«
    0.09
    èķĸ
    0.09
    еÑģп
    0.09
    Activations Density 0.459%

    No Known Activations