© 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. 648
    Prev
    Next
    INDEX
    Explanations

    extra virgin olive

    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¸Ģçľĭ
    -0.09
    åĵ¥
    -0.09
    æıIJéĢŁ
    -0.09
    æŃ¥æŃ¥
    -0.09
     nonlinear
    -0.09
    ä¸įé«ĺ
    -0.09
    åĬŀå®ŀäºĭ
    -0.09
    å¤įåį°
    -0.08
    大åĪĩ
    -0.08
    lat
    -0.08
    POSITIVE LOGITS
     khuôn
    0.10
    èIJĦ
    0.10
    çĶļ
    0.10
    æ¸ij
    0.09
    GES
    0.09
    æľ¬æĬ¥
    0.09
    黥
    0.08
    å¾½
    0.08
    OOD
    0.08
    _drive
    0.08
    Activations Density 0.057%

    No Known Activations