© 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. 6021
    Prev
    Next
    INDEX
    Explanations

    contrast or opposition

    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
    çĦ¶èĢĮ
    -0.08
    æĹłäºº
    -0.08
    lich
    -0.08
    åĩ«
    -0.08
    æŃ£åĽłä¸º
    -0.08
    ä¸Ģå¼Ģå§ĭå°±
    -0.08
    ag
    -0.08
    INAL
    -0.08
    wing
    -0.08
    UserRole
    -0.07
    POSITIVE LOGITS
     basically
    0.09
    åŁºæľ¬ä¸Ĭ
    0.09
    oodles
    0.09
     Bye
    0.09
    _SPI
    0.08
     Favor
    0.08
    èĤĮ
    0.08
    çıįçıł
    0.08
    TÄ°
    0.08
    æĢ»ä¹ĭ
    0.08
    Activations Density 0.088%

    No Known Activations