© 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. 59345
    Prev
    Next
    INDEX
    Explanations

    demand, supply, or economic conditions

    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
    缣
    -0.10
    ç»ŀ
    -0.10
    æĮ«
    -0.10
    å¸IJåı·
    -0.10
    ä¸įåıªæĺ¯
    -0.09
    åħ»èĢģä¿ĿéĻ©
    -0.09
    éĹ®çŃĶ
    -0.09
    æĪ¿ç§Ł
    -0.09
    éĺµ
    -0.09
    åĮ»ç§ij
    -0.09
    POSITIVE LOGITS
    èī²è°ĥ
    0.10
    ç«£
    0.09
    åħľ
    0.08
    ç¿ħ
    0.08
     firepower
    0.08
    奪
    0.08
    ç´§å¼ł
    0.08
     excess
    0.08
    Disallow
    0.08
    bek
    0.08
    Activations Density 0.038%

    No Known Activations