© 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. 6080
    Prev
    Next
    INDEX
    Explanations

    power relations

    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
    æīĢå¾Ĺ
    -0.10
    天æīį
    -0.09
    çĽĨåľ°
    -0.09
    æ·±åĮĸæĶ¹éĿ©
    -0.09
    è¿
    -0.09
    ç¾ŀ
    -0.08
    çķ´
    -0.08
    æĻ¯å¾·
    -0.08
    ä¸ļ绩
    -0.08
    è¿ĻäºĽéĹ®é¢ĺ
    -0.08
    POSITIVE LOGITS
    ieber
    0.10
    fully
    0.10
    ?v
    0.09
    [arr
    0.09
    æŁĦ
    0.09
     Strauss
    0.09
    æݨèįIJéĺħ读
    0.09
    æĿ¼
    0.09
    .AsyncTask
    0.09
    ähl
    0.09
    Activations Density 0.022%

    No Known Activations