© 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. 63922
    Prev
    Next
    INDEX
    Explanations

    appropriate follow-ups

    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¸ĢåĪĨéĴŁ
    -0.10
    minutes
    -0.09
     Glover
    -0.08
    åĬĽäºī
    -0.08
     rer
    -0.08
    Mail
    -0.08
    HANDLE
    -0.08
    å²·
    -0.08
     Mail
    -0.07
    .colorbar
    -0.07
    POSITIVE LOGITS
    对åºĶçļĦ
    0.10
    asper
    0.10
    åħļç»Ħç»ĩ
    0.10
    ÑĪе
    0.09
    åľºåIJĪ
    0.09
    æĶ¿åºľéĥ¨éŨ
    0.09
    缸åºĶçļĦ
    0.09
     дело
    0.09
     (?)
    0.09
    年级
    0.09
    Activations Density 0.205%

    No Known Activations