© 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. 40054
    Prev
    Next
    INDEX
    Explanations

    screen size specifications

    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
    çļĦåģļæ³ķ
    -0.10
     полÑı
    -0.09
    æİĪ
    -0.09
    PELL
    -0.09
    é¾
    -0.09
    èįī
    -0.09
    ÎŃ
    -0.08
    _codegen
    -0.08
    åĸĿäºĨ
    -0.08
    è²Ŀ
    -0.08
    POSITIVE LOGITS
    åºķèķ´
    0.10
     ATK
    0.09
    atra
    0.09
     size
    0.09
    樱æ¡ĥ
    0.09
    rai
    0.08
    çī¹èī²çļĦ
    0.08
    ä»ij
    0.08
    管çIJĨæĿ¡ä¾ĭ
    0.08
    æ¤IJ
    0.08
    Activations Density 0.145%

    No Known Activations