© 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. 47523
    Prev
    Next
    INDEX
    Explanations

    miniaturization or chemical transformation

    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
    sWith
    -0.13
    ç¿Ķ
    -0.10
    éĹ¾
    -0.10
    ä½¼
    -0.10
    lessly
    -0.10
    erner
    -0.09
    åºŁå¼ĥçī©
    -0.09
     Sawyer
    -0.09
    ä¸Ŀ绸
    -0.09
    âĺİ
    -0.09
    POSITIVE LOGITS
    ç¨ĭ度
    0.12
    è¶ĭåĬ¿
    0.10
    ëIJľ
    0.09
    è¿Ľç¨ĭ
    0.09
    è¿ĩç¨ĭ
    0.09
    è¿ĩç¨ĭä¸Ń
    0.09
    è¹ĩ
    0.08
     process
    0.08
    ist
    0.08
    éģĵè·¯ä¸Ĭ
    0.08
    Activations Density 0.300%

    No Known Activations