© 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. 16539
    Prev
    Next
    INDEX
    Explanations

    advertising platform

    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
    笥
    -0.11
    è½»
    -0.10
    ì²ĺ리
    -0.10
    è¼ķ
    -0.10
    ваÑĤ
    -0.10
    anko
    -0.09
    èĢ³è¾¹
    -0.09
    å®ıè§Ĥç»ıæµİ
    -0.09
    éĽ¶é£Ł
    -0.09
    纯
    -0.09
    POSITIVE LOGITS
     heir
    0.10
    èģĺ请
    0.09
    ä¸įæĩĪ
    0.09
    ç»ĵ
    0.08
    _cast
    0.08
    å¥ĩ迹
    0.08
    æģIJ
    0.08
    çłº
    0.08
    å¤ĸ壳
    0.08
    æķ´å¤©
    0.08
    Activations Density 0.039%

    No Known Activations