© 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. 852
    Prev
    Next
    INDEX
    Explanations

    Jessica Lange, Morse, PASCAL, U.S

    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
     ë¶Ī구íķĺê³ł
    -0.13
    istic
    -0.11
    ially
    -0.10
    ustin
    -0.09
    æĻĤåĢĻ
    -0.09
    ı
    -0.09
    tempts
    -0.09
    ../
    -0.09
    iese
    -0.09
    cake
    -0.08
    POSITIVE LOGITS
    çĦ¶æĺ¯
    0.16
    ãģĹãģ¾ãģĦ
    0.12
    ently
    0.11
    ally
    0.11
    ãģĹãģ¾ãģĨ
    0.10
    è¡·
    0.10
    forth
    0.10
    ald
    0.10
     dÃłng
    0.10
    å®ļäºĨ
    0.10
    Activations Density 0.385%

    No Known Activations