© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 91299
    Prev
    Next
    INDEX
    Explanations

    determiners following verbs

    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
    Not in Any Lists

    No Comments

    Negative Logits
     ogni
    -0.11
     além
    -0.11
    abo
    -0.11
     giÃł
    -0.11
    antha
    -0.11
    ati
    -0.10
    enever
    -0.10
    ones
    -0.10
     aunque
    -0.10
     mund
    -0.10
    POSITIVE LOGITS
     some
    0.54
    some
    0.43
     Some
    0.38
    Some
    0.36
     SOME
    0.32
    äºĽ
    0.30
    .some
    0.29
     einige
    0.27
     quelques
    0.27
    _some
    0.25
    Activations Density 0.727%

    No Known Activations