© 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. 63828
    Prev
    Next
    INDEX
    Explanations

    douchbag, dork magnet, anal retentiveness, cocksucking

    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
    isphere
    -0.11
    åĦĭ
    -0.10
    轶
    -0.10
    ä½ļ
    -0.09
    岬
    -0.09
    LAY
    -0.09
     Mae
    -0.09
    IDA
    -0.09
    çıĤ
    -0.09
    ç¢Į
    -0.09
    POSITIVE LOGITS
    st
    0.10
    èĪ¬çļĦ
    0.09
    ifest
    0.09
    hausen
    0.09
    çĶ·åŃIJ
    0.09
    ÑĩеÑģÑĤво
    0.09
    es
    0.08
    Ø´ÙĪر
    0.08
    er
    0.08
    uco
    0.08
    Activations Density 0.017%

    No Known Activations