© 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. 29447
    Prev
    Next
    INDEX
    Explanations

    clothing styles

    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
    ableObject
    -0.11
    综åIJĪä½ĵ
    -0.10
    æĶ¾å¤§
    -0.10
    èĬĴæŀľ
    -0.09
    åĴ¨
    -0.09
    大æłij
    -0.09
    æĶ¹è£ħ
    -0.09
    Essay
    -0.09
    åºŁçī©
    -0.09
    æ³·
    -0.09
    POSITIVE LOGITS
    criptor
    0.09
    اÙĤ
    0.09
    è¢ĸ
    0.09
    _sources
    0.09
    ertype
    0.08
    é«ĺçŃī
    0.08
    åħ»æ®ĸæĪ·
    0.08
    åħļå§Ķ
    0.08
     stud
    0.08
    @js
    0.08
    Activations Density 0.052%

    No Known Activations