© 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. 677
    Prev
    Next
    INDEX
    Explanations

    qualified, knowledge, train

    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
    å¤į
    -0.10
    ked
    -0.09
    纵åIJij
    -0.08
    å¤ĸæĿ¥
    -0.08
    iore
    -0.08
    utory
    -0.08
    rzy
    -0.08
    ç»ıå¼Ģ
    -0.08
     limited
    -0.08
    å¸ĪçĶŁ
    -0.08
    POSITIVE LOGITS
    èĥľä»»
    0.13
    èģĮä½į
    0.13
    å²Ĺä½į
    0.12
    æ¡£æ¡Ī
    0.11
    ä»»èģĮ
    0.11
    ç´łè´¨
    0.11
    å´
    0.10
    Skills
    0.10
    ä¸Ĭå²Ĺ
    0.10
    _required
    0.10
    Activations Density 0.034%

    No Known Activations