© 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. 6064
    Prev
    Next
    INDEX
    Explanations

    time periods

    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
    ä»Ĭ
    -0.12
    åĪ»
    -0.11
    ä¸ĢåĪ»
    -0.10
    æ´ŀå¯Ł
    -0.10
    æµģéĢļ
    -0.09
    ä¸Ģéĺµ
    -0.09
    å¹Ħ
    -0.09
    odiac
    -0.09
    åĺ²ç¬ij
    -0.09
    .ids
    -0.09
    POSITIVE LOGITS
    ë§Īëĭ¤
    0.11
    _PAD
    0.09
    èĻ¢
    0.09
    廪
    0.08
    quis
    0.08
     euth
    0.08
    ä¸įä¸ĭ
    0.08
    ÏĤ
    0.08
    LEM
    0.08
    åħ¬å¼Ģ
    0.08
    Activations Density 0.063%

    No Known Activations