© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113562
    Prev
    Next
    INDEX
    Explanations

    was/were past tense descriptions

    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
     currently
    -0.16
     now
    -0.16
     presently
    -0.13
     becoming
    -0.11
     unlikely
    -0.11
    now
    -0.11
    currently
    -0.10
     Currently
    -0.10
     usually
    -0.09
     increasingly
    -0.09
    POSITIVE LOGITS
    /is
    0.21
     instrumental
    0.15
     successful
    0.14
     unsuccessful
    0.13
    abi
    0.13
     previously
    0.11
     victorious
    0.11
     able
    0.11
     born
    0.11
    successful
    0.11
    Activations Density 0.437%

    No Known Activations