© 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. 60724
    Prev
    Next
    INDEX
    Explanations

    functional programming languages

    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
    å¿ĥ头
    -0.08
    Scalar
    -0.08
    Ted
    -0.08
    ä¸įèµ·
    -0.08
    лив
    -0.08
    hed
    -0.07
    èĻİ
    -0.07
    xED
    -0.07
    两端
    -0.07
    ione
    -0.07
    POSITIVE LOGITS
    .undefined
    0.11
    æĭĩ
    0.10
    åķ¡
    0.10
    éĵĻ
    0.09
     иÑģкÑĥÑģÑģÑĤв
    0.09
    å±İ
    0.09
    寮
    0.09
    çİĭåĽ½
    0.09
    渥
    0.09
    æĦıå¢ĥ
    0.09
    Activations Density 0.418%

    No Known Activations