© 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. 24262
    Prev
    Next
    INDEX
    Explanations

    laundry room

    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
    æĪ´ä¸Ĭ
    -0.10
    è¡Ģ管
    -0.10
    å®ŀè´¨æĢ§
    -0.10
    çĴĭ
    -0.10
    à¹Ģà¸ĸ
    -0.10
    åĩºçĶŁäºİ
    -0.09
    æĪ´çĿĢ
    -0.09
    igned
    -0.09
    çªģçł´
    -0.09
    èĽĭç³ķ
    -0.09
    POSITIVE LOGITS
    æ´Ĺè¡£
    0.17
     laundry
    0.13
     Laundry
    0.12
    æ´Ĺ涤
    0.10
    æĻ¾
    0.10
    æ±Łä¸ľ
    0.09
    æ´ĹåĩĢ
    0.09
    åŁºæľ¬åİŁåĪĻ
    0.09
     quần
    0.09
    è¡£çī©
    0.08
    Activations Density 0.041%

    No Known Activations