© 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. 40430
    Prev
    Next
    INDEX
    Explanations

    radial, radius, and radial directions

    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
    ritt
    -0.09
    è¿ľè¿ľ
    -0.08
    æľªç»ı
    -0.08
    erÃŃa
    -0.08
    ewe
    -0.08
     pitched
    -0.08
    æģ¼
    -0.08
     kidd
    -0.07
    æŃ»åIJİ
    -0.07
    ÄŁu
    -0.07
    POSITIVE LOGITS
    roach
    0.11
    ally
    0.10
    ä¼
    0.10
    大æłij
    0.10
    ity
    0.09
    è¿©
    0.09
    -shell
    0.09
     dise
    0.09
     spokes
    0.09
    æľĭ
    0.09
    Activations Density 0.081%

    No Known Activations