© 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. 40269
    Prev
    Next
    INDEX
    Explanations

    stimulus response/dollars

    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
    说æĺİ书
    -0.09
    hus
    -0.09
    峤
    -0.09
    лад
    -0.08
    ials
    -0.08
    orses
    -0.08
    ç´§æī£
    -0.08
    usal
    -0.08
    old
    -0.08
     newly
    -0.08
    POSITIVE LOGITS
    åĪ¸
    0.11
    æ´¾
    0.09
    combe
    0.09
    ì±ħ
    0.09
    大çīĩ
    0.09
    麽
    0.09
    ä¸įæİĴéĻ¤
    0.09
    ORY
    0.08
    æ¶ķ
    0.08
    æ´¾éģ£
    0.08
    Activations Density 0.006%

    No Known Activations