© 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. 33359
    Prev
    Next
    INDEX
    Explanations

    verbs followed by "that" or "he"

    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
     whats
    -0.12
    nap
    -0.11
    coop
    -0.10
    sted
    -0.10
    ingle
    -0.10
    erk
    -0.10
    ure
    -0.09
    orch
    -0.09
    cke
    -0.09
    uft
    -0.09
    POSITIVE LOGITS
     beforehand
    0.18
    —as
    0.17
     afterward
    0.17
    —in
    0.14
    —even
    0.14
    —at
    0.14
     via
    0.13
     throughout
    0.13
    —for
    0.13
     afterwards
    0.13
    Activations Density 0.504%

    No Known Activations