© 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. 16901
    Prev
    Next
    INDEX
    Explanations

    influential people, groups, or things

    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
    agu
    -0.09
    ewed
    -0.09
    ru
    -0.09
    æĽĻåħī
    -0.08
    лен
    -0.08
    èģĶæĥ³
    -0.08
    æ®·
    -0.08
    olem
    -0.08
    ç²¾åįİ
    -0.08
     Lug
    -0.08
    POSITIVE LOGITS
    çļĦå½±åĵį
    0.10
     ÙĦÙĦغاÙĬØ©
    0.09
    ãģªãĤĤãģ®
    0.09
    å½±åĵįåĬĽ
    0.09
    åħ´ä¸ļ
    0.09
    è¶ħåĩº
    0.09
    å½±åĵįåĬĽçļĦ
    0.09
    à¹Ģà¸ĸ
    0.09
     Rath
    0.08
    å±ħ
    0.08
    Activations Density 0.012%

    No Known Activations