© 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. 29501
    Prev
    Next
    INDEX
    Explanations

    Amtrak, Corning, Amgen

    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
    ä¹İ
    -0.10
    éĩĩ
    -0.10
    nuts
    -0.09
    lobe
    -0.09
    samp
    -0.09
    ared
    -0.08
    erman
    -0.08
    å»ĵ
    -0.08
    uz
    -0.08
    ario
    -0.08
    POSITIVE LOGITS
    ÃŃc
    0.10
    atedRoute
    0.10
    lek
    0.09
    ESA
    0.09
    æ®Ĭ
    0.09
    ỡ
    0.09
    lef
    0.09
    æĿľåħ°
    0.09
    rose
    0.08
    çĸı
    0.08
    Activations Density 0.005%

    No Known Activations