© 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. 64009
    Prev
    Next
    INDEX
    Explanations

    taxes, pricing, and policy changes

    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
    è·Łä¸įä¸Ĭ
    -0.10
    è´¯
    -0.10
    éľŀ
    -0.10
    rat
    -0.10
    orp
    -0.10
    zym
    -0.09
    éĥ½ä¸įæķ¢
    -0.09
    以èĩ´
    -0.09
     gyr
    -0.09
    åģļå®Į
    -0.09
    POSITIVE LOGITS
    åĬŀæ³ķ
    0.10
    æľºåĪ¶
    0.10
     mechanism
    0.08
    缸åıį
    0.08
    STM
    0.08
    reso
    0.08
     Lok
    0.08
    ç»ĻåĬĽ
    0.08
    èĬ±å¼Ģ
    0.08
    _measure
    0.08
    Activations Density 0.156%

    No Known Activations