© 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. 24141
    Prev
    Next
    INDEX
    Explanations

    opponents or everyone worldwide

    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
    åĿIJåľ¨
    -0.10
    ÙĨص
    -0.10
    å¤ļåľ°
    -0.09
    çłŃ
    -0.09
    è¿·æĥij
    -0.09
    å¾Īå¤ļ人
    -0.09
    ç¾ļ
    -0.09
    çŃīçī¹çĤ¹
    -0.08
     egret
    -0.08
    æĭŁ
    -0.08
    POSITIVE LOGITS
    alone
    0.14
     alone
    0.12
    æķ´ä½ĵ
    0.11
    以å¤ĸ
    0.10
    çļĦæķ´ä½ĵ
    0.10
     ìłĦì²´
    0.10
    ãģłãģijãģ§
    0.10
    croft
    0.10
    åIJĪ计
    0.09
    æĢ»åħ±
    0.09
    Activations Density 0.276%

    No Known Activations