© 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. 59366
    Prev
    Next
    INDEX
    Explanations

    Zimmerman trial

    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
     вÑĢемен
    -0.11
    åŃ¦å®¶
    -0.10
    imet
    -0.10
    enance
    -0.09
    çijĻ
    -0.09
    åŀŃ
    -0.09
    ikk
    -0.09
    heet
    -0.09
    æ³±
    -0.09
    äºĶæĺŁ
    -0.09
    POSITIVE LOGITS
    erator
    0.09
    usk
    0.09
    ault
    0.09
    er
    0.08
    aud
    0.08
    halt
    0.08
    ooter
    0.08
    edReader
    0.08
    equality
    0.08
    оÑĤов
    0.08
    Activations Density 0.003%

    No Known Activations