© 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. 50852
    Prev
    Next
    INDEX
    Explanations

    nintendo video 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
     anth
    -0.10
     Incoming
    -0.10
     Maver
    -0.09
     Kerala
    -0.09
     derby
    -0.09
     Pont
    -0.09
     dimension
    -0.08
     Plants
    -0.08
    ecn
    -0.08
    amba
    -0.08
    POSITIVE LOGITS
     Gan
    0.15
     Zelda
    0.15
     Hy
    0.15
     Link
    0.14
     Ger
    0.12
    gan
    0.12
     dungeon
    0.12
     BOT
    0.12
    Link
    0.11
     Kak
    0.10
    Activations Density 0.014%

    No Known Activations