© 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. 63760
    Prev
    Next
    INDEX
    Explanations

    paying attention

    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
    ниÑĩ
    -0.10
    æģ°å¥½
    -0.09
     paw
    -0.09
    飵
    -0.09
    -ended
    -0.08
    æ´ĭ
    -0.08
    หล
    -0.08
    imore
    -0.08
    tech
    -0.08
    ILED
    -0.08
    POSITIVE LOGITS
    çģ¾éļ¾
    0.09
    åįĹåĮĹ
    0.09
    æªĦ
    0.09
    obl
    0.09
    ä¸įè´Ł
    0.08
    èħ¦
    0.08
    çĶ¨å¿ĥ
    0.08
    æĺı
    0.08
    示
    0.08
     mis
    0.08
    Activations Density 0.033%

    No Known Activations