© 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. 26263
    Prev
    Next
    INDEX
    Explanations

    misunderstanding or misinterpretation

    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
    à¹Ĥà¸ģ
    -0.08
     ниÑĩ
    -0.08
    æĻĭ
    -0.08
    .createObject
    -0.08
    èµ·æĿ¥
    -0.08
    éĻĮ
    -0.08
    符åIJĪ
    -0.08
    .ObjectId
    -0.08
    ç»´å°Ķ
    -0.08
    entai
    -0.08
    POSITIVE LOGITS
    ä»Ģä¹Īæĺ¯
    0.11
     Bros
    0.10
    ç²¾é«ĵ
    0.10
    è¿ĺ以为
    0.10
    ä»Ģä¹Īåı«
    0.10
    éĿ¢çĽ®
    0.10
    è½Ń
    0.10
    以çĤº
    0.09
    /jav
    0.09
     entirely
    0.09
    Activations Density 0.060%

    No Known Activations