© 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. 26055
    Prev
    Next
    INDEX
    Explanations

    isolation and confinement

    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
    äºī夺
    -0.10
    éŀį
    -0.10
    绥
    -0.10
    æĪijè¿ĺæĺ¯
    -0.09
    å¥ĸåĬ±
    -0.09
    æĹħ游æĻ¯åĮº
    -0.09
    ä¸Ģ个å¤ļ
    -0.09
    å½ĵæĻļ
    -0.09
    èĥ½åĬĽå¼º
    -0.09
    aku
    -0.08
    POSITIVE LOGITS
    å°ģéĹŃ
    0.17
    éļĶ离
    0.15
    å¤ĸçķĮ
    0.13
    ä¸įéĢļ
    0.13
     isolation
    0.12
    isol
    0.12
    éĹŃ
    0.10
     isol
    0.09
    ä¸¥æł¼
    0.09
    ç»Ī
    0.09
    Activations Density 0.110%

    No Known Activations