© 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. 64015
    Prev
    Next
    INDEX
    Explanations

    Montreal Canadiens

    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
    -0.13
    ging
    -0.10
    ernel
    -0.10
    uate
    -0.10
    istration
    -0.09
    UAL
    -0.09
    uilt
    -0.09
    adel
    -0.08
     veget
    -0.08
    ories
    -0.08
    POSITIVE LOGITS
    ship
    0.11
    liness
    0.10
    ers
    0.10
    å¾Ĺä½ı
    0.09
     Canadiens
    0.09
    gomery
    0.09
    ists
    0.08
    ambda
    0.08
    æ·¼
    0.08
    ment
    0.08
    Activations Density 0.002%

    No Known Activations