© 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. 12204
    Prev
    Next
    INDEX
    Explanations

    traffic congestion and jams

    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
    æĢĢæĬ±
    -0.11
    æĮĤåı·
    -0.10
    ä¸ĢéĹª
    -0.09
    æĸ¹æīį
    -0.09
    curity
    -0.09
    çĭIJ
    -0.09
    æłijæŀĿ
    -0.09
    æĢ§åij½
    -0.09
    åħ¨ç¤¾ä¼ļ
    -0.09
     Mah
    -0.09
    POSITIVE LOGITS
    åĽ´ç»ķ
    0.10
     Lan
    0.08
     Cole
    0.08
    çļĦåľ°æĸ¹
    0.08
    仪
    0.08
    æĭľ
    0.08
    åĵŃäºĨ
    0.08
     lan
    0.08
     optarg
    0.08
    ëĤ¨
    0.08
    Activations Density 0.013%

    No Known Activations