© 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. 60876
    Prev
    Next
    INDEX
    Explanations

    sport and athletics

    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
    ARY
    -0.10
    åĬ¡å®ŀ
    -0.09
    tern
    -0.09
    éĴ»çŁ³
    -0.09
    æ´¾
    -0.09
    æ¹¾åĮº
    -0.09
    æľīéĹ®é¢ĺ
    -0.09
    åħĢ
    -0.09
    aye
    -0.09
    åįĩ
    -0.08
    POSITIVE LOGITS
    vents
    0.08
    hue
    0.08
    IMG
    0.08
    exc
    0.08
     Exc
    0.08
     IMG
    0.07
     Lap
    0.07
    зн
    0.07
     ink
    0.07
    èĪĨæĥħ
    0.07
    Activations Density 0.007%

    No Known Activations