© 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. 6253
    Prev
    Next
    INDEX
    Explanations

    season or seasonal ingredients

    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
    çģ¯çģ«
    -0.10
    éħ
    -0.09
    驺
    -0.09
    çģı
    -0.08
    æī©
    -0.08
     Че
    -0.08
    æī©å¤§
    -0.08
    etty
    -0.08
    YPE
    -0.08
     Nights
    -0.08
    POSITIVE LOGITS
    åŃ£èĬĤ
    0.28
    åĽĽåŃ£
    0.26
     seasons
    0.25
     season
    0.23
     seasonal
    0.23
     Seasons
    0.22
    åŃ£
    0.22
    Season
    0.21
    season
    0.21
    _season
    0.20
    Activations Density 0.089%

    No Known Activations