© 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. 6743
    Prev
    Next
    INDEX
    Explanations

    past tense 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
    ucci
    -0.10
     pars
    -0.08
    eny
    -0.08
     AC
    -0.08
     Keith
    -0.08
     Fang
    -0.08
    erp
    -0.08
    .neo
    -0.07
     Shaw
    -0.07
     ac
    -0.07
    POSITIVE LOGITS
    orent
    0.10
    uyo
    0.10
     Rah
    0.10
     Vander
    0.10
    onta
    0.10
    esa
    0.10
     subst
    0.10
    icle
    0.10
    ummer
    0.10
     Composite
    0.10
    Activations Density 0.247%

    No Known Activations