© 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. 17737
    Prev
    Next
    INDEX
    Explanations

    recent 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
     eventually
    -0.21
     initially
    -0.19
     presently
    -0.18
     eventual
    -0.18
     originally
    -0.18
     still
    -0.18
     someday
    -0.17
     today
    -0.17
     soon
    -0.17
     currently
    -0.16
    POSITIVE LOGITS
     increasingly
    0.19
     trend
    0.14
     resurgence
    0.11
     begun
    0.11
     increasing
    0.11
     emerging
    0.10
     trending
    0.10
     noticed
    0.09
     seems
    0.09
     focus
    0.09
    Activations Density 0.246%

    No Known Activations