© 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. 18614
    Prev
    Next
    INDEX
    Explanations

    toy

    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
     overtime
    -0.06
    isco
    -0.06
    $ar
    -0.06
     Mug
    -0.06
     verm
    -0.06
    _BEGIN
    -0.06
    aira
    -0.06
     Dank
    -0.06
     Artem
    -0.06
     OG
    -0.06
    POSITIVE LOGITS
    Toy
    0.14
     Toy
    0.12
     toy
    0.12
     Toys
    0.11
     crib
    0.11
     TTC
    0.11
    toy
    0.11
     Playground
    0.11
     dolls
    0.10
     Graves
    0.10
    Activations Density 0.025%

    No Known Activations