© 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. 16895
    Prev
    Next
    INDEX
    Explanations

    selling, sales, shop

    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
    osta
    -0.09
     dissect
    -0.09
    oste
    -0.09
    iore
    -0.09
    Gene
    -0.08
    è¦Ĩ
    -0.08
    SURE
    -0.08
     pole
    -0.08
    æľį
    -0.08
    ì°©
    -0.08
    POSITIVE LOGITS
    à¸Ļะà¸Ħะ
    0.10
    交ä¼ļ
    0.09
    å¤ĸ交éĥ¨
    0.09
    åŃĽ
    0.09
    å®ļä»·
    0.09
    èİĵ
    0.08
     Etsy
    0.08
    è§Ħ模
    0.08
    èĿł
    0.08
    Shipping
    0.08
    Activations Density 0.023%

    No Known Activations