© 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. 29511
    Prev
    Next
    INDEX
    Explanations

    holders and related items

    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
    樵
    -0.10
    åĨĻçļĦ
    -0.09
    ç¾¹
    -0.09
    ç¼®
    -0.08
    çļĦä¸Ģ项
    -0.08
    0
    -0.08
    5
    -0.08
    à¹Ĥà¸Ľ
    -0.08
    ule
    -0.08
    åĢº
    -0.08
    POSITIVE LOGITS
    仪
    0.10
    京津
    0.10
    åĩºåĬ¨
    0.09
    æµģåĩº
    0.09
    -columns
    0.09
    IVAL
    0.09
    ẻ
    0.09
    ivol
    0.09
    ä¾
    0.09
    Ẻ
    0.08
    Activations Density 0.169%

    No Known Activations