© 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. 40393
    Prev
    Next
    INDEX
    Explanations

    letters to editors

    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
    éĴį
    -0.09
    çŃĸ
    -0.08
    èĦ²
    -0.08
    æķŀ
    -0.08
    urg
    -0.08
    æĢł
    -0.08
    ä¸įåĬ¨
    -0.08
    erged
    -0.08
    æµģè¡Į
    -0.08
    bill
    -0.08
    POSITIVE LOGITS
    åıįé¦Ī
    0.11
    ÐŀÑģ
    0.09
    é«ĺæ½®
    0.09
    æĦıè§ģ
    0.09
    çĥŃå¿ĥ
    0.09
    樱
    0.08
    è¿Ļ段æŶéĹ´
    0.08
    èĥĢ
    0.08
    åıįåĵį
    0.08
    .ci
    0.08
    Activations Density 0.014%

    No Known Activations