© 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. 24325
    Prev
    Next
    INDEX
    Explanations

    conversational interjections and affirmations

    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
    ogle
    -0.10
    variants
    -0.10
    èIJ¥ä¸ļæĶ¶åħ¥
    -0.10
    æİ¥çĿĢ
    -0.09
    èĩ³æĸ¼
    -0.09
    æİ¥èijĹ
    -0.08
    kim
    -0.08
    osen
    -0.08
    æĥħèĬĤ
    -0.08
    icontrol
    -0.08
    POSITIVE LOGITS
    é¹Ĭ
    0.09
    ä¹ĭä½Ļ
    0.08
    åĪ°æľĢåIJİ
    0.08
    é¹Į
    0.08
    ilor
    0.08
    è¾ĵç»Ļ
    0.08
    循
    0.07
    缩
    0.07
     Portable
    0.07
    SHIP
    0.07
    Activations Density 0.017%

    No Known Activations