© 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. 927
    Prev
    Next
    INDEX
    Explanations

    summary judgment or order

    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
    马åĬĽ
    -0.11
    ä¸Ģç¢Ĺ
    -0.10
    ä¸Ģè¶Ł
    -0.09
    çĶŁæĦı
    -0.09
    inea
    -0.09
    è¿Ļè¯Ŀ
    -0.09
    ä¸įè¿ľå¤Ħ
    -0.09
    麻çĹ¹
    -0.09
    åĨįè§ģ
    -0.09
    å¸Ŀ
    -0.09
    POSITIVE LOGITS
    estate
    0.09
    çĵľ
    0.09
    -preview
    0.09
    æŀľæĸŃ
    0.09
    æıIJåīį
    0.08
     mis
    0.08
     Ore
    0.08
    å»ºåĽ½
    0.08
    zer
    0.08
     nom
    0.08
    Activations Density 0.459%

    No Known Activations