© 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. 59195
    Prev
    Next
    INDEX
    Explanations

    although, though

    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
    ä»Ģä¹Īåij¢
    -0.12
     zwar
    -0.12
    ä¸įä½Ĩ
    -0.11
    è¦ģä¹Ī
    -0.10
    主è¦ģæľī
    -0.10
    èĻ½çĦ¶
    -0.10
    éĽĸçĦ¶
    -0.09
    èµ·çłģ
    -0.09
    åħħ
    -0.09
    èĢĮä¸Ķè¿ĺ
    -0.09
    POSITIVE LOGITS
    izard
    0.10
    ä¸Ģ度
    0.10
    ä¸įä¹ı
    0.09
    uche
    0.09
    为ä¹ĭ
    0.08
     Chick
    0.08
    ÑĢоÑģ
    0.08
     некоÑĤоÑĢÑĭе
    0.08
    uckle
    0.08
    屡
    0.08
    Activations Density 0.056%

    No Known Activations