© 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. 26415
    Prev
    Next
    INDEX
    Explanations

    entrusted, given, assigned, issued, supplied

    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
    inis
    -0.09
     Balt
    -0.09
    éĽĢ
    -0.08
    rial
    -0.08
    å¨ī
    -0.08
    felt
    -0.08
    edly
    -0.08
    åħĪ导
    -0.08
    ấu
    -0.08
    eref
    -0.08
    POSITIVE LOGITS
    ç»ĻäºĨ
    0.19
    ç»ĻäºĨæĪij
    0.17
    èµIJ
    0.16
    æİĪäºĪ
    0.15
    ç»ĻäºĪäºĨ
    0.15
    ç»ĻäºĪ
    0.15
    交ç»Ļ
    0.14
    ç»ĻåĩºäºĨ
    0.14
    ãĤĴä¸İãģĪ
    0.14
    給äºĪ
    0.14
    Activations Density 0.095%

    No Known Activations