© 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. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 46219
    Prev
    Next
    INDEX
    Explanations

    Dragon Ball Z games

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_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
     carousel
    -0.11
     ($.
    -0.10
     flutter
    -0.09
    ëĭĪ
    -0.09
     touch
    -0.09
     Tot
    -0.09
    yll
    -0.09
     calibrated
    -0.09
     flock
    -0.09
     feed
    -0.09
    POSITIVE LOGITS
     Goku
    0.23
     Veget
    0.13
     Naruto
    0.12
     anime
    0.12
     Sai
    0.12
     manga
    0.12
    anime
    0.11
     Earth
    0.11
     Gundam
    0.11
     GT
    0.11
    Activations Density 0.006%

    No Known Activations