© 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. 12425
    Prev
    Next
    INDEX
    Explanations

    online selling and auctions

    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
    izedName
    -0.09
    æģĴ
    -0.09
    2
    -0.09
    æĪļ
    -0.08
    è¾ķ
    -0.08
     внеÑĪне
    -0.08
    soup
    -0.08
    åIJįæ°Ķ
    -0.08
     Til
    -0.08
    éĢĤåIJĪèĩªå·±
    -0.08
    POSITIVE LOGITS
    çī©åĵģ
    0.11
    转让
    0.10
     kole
    0.10
    翦
    0.10
    äºĮæīĭ
    0.10
    缮çĿ¹
    0.09
    åĽŀå¿Ĩ
    0.09
    _emit
    0.09
    买家
    0.09
    å·´å·´
    0.09
    Activations Density 0.031%

    No Known Activations