© 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. 47694
    Prev
    Next
    INDEX
    Explanations

    offensive or abusive language

    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
    isper
    -0.09
    FileType
    -0.08
    emen
    -0.08
    åį´è¢«
    -0.08
    ç²ij
    -0.08
    æ·¦
    -0.08
    uly
    -0.08
    é³ı
    -0.08
    享åıĹåĪ°
    -0.08
    çĪµå£«
    -0.08
    POSITIVE LOGITS
    广éĺĶçļĦ
    0.10
    åĢ¾åIJij
    0.10
    ê¸Ģ
    0.10
    æľ¬ç«Ļ
    0.09
    çĬ¯è§Ħ
    0.09
     quot
    0.09
    æij¹
    0.09
    纡
    0.09
    çĶ¥
    0.09
    èĩªè§ī
    0.09
    Activations Density 0.012%

    No Known Activations