© 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. 63820
    Prev
    Next
    INDEX
    Explanations

    HTML input type

    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
    Not in Any Lists

    No Comments

    Negative Logits
    åĤ»
    -0.09
    ä¸Ńç§ĭ
    -0.09
    wing
    -0.09
    漫éķ¿çļĦ
    -0.09
    èĤī
    -0.09
    éĺ¶
    -0.09
    å¾Īå¼Ģå¿ĥ
    -0.08
    èĵ¬
    -0.08
    SEC
    -0.08
    èİ«æĸ¯ç§ij
    -0.08
    POSITIVE LOGITS
    .setAction
    0.09
    屯
    0.09
    æŶä¸į
    0.09
    -ball
    0.08
    åľ¨æѤä¹ĭåīį
    0.08
    åħĪ导
    0.08
    .DialogResult
    0.08
    ×ŀצ
    0.08
    端æŃ£
    0.08
    åħ¨çIJĥæľĢ大
    0.08
    Activations Density 0.915%

    No Known Activations