© 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. 40426
    Prev
    Next
    INDEX
    Explanations

    reset

    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
    yard
    -0.10
    htar
    -0.09
    绣
    -0.09
     Burnett
    -0.09
     Yuri
    -0.09
    å®ĹæŨ
    -0.09
    è²Į
    -0.09
    åºķèķ´
    -0.08
    дÑĢ
    -0.08
    æŨ
    -0.08
    POSITIVE LOGITS
    ting
    0.10
    imate
    0.10
    å·¥ä½ľä½ľé£İ
    0.09
    æĦ¿æľĽ
    0.08
    imals
    0.08
    äºĨæĪijçļĦ
    0.08
    ä¸įå·²
    0.08
    ť
    0.08
    tings
    0.08
    iat
    0.08
    Activations Density 0.022%

    No Known Activations