© 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. 90353
    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
    andin
    -0.10
    >manual
    -0.10
     Erick
    -0.10
    ces
    -0.10
     Agricult
    -0.10
    IDL
    -0.10
     whence
    -0.10
     intellectually
    -0.09
     quo
    -0.09
    prech
    -0.09
    POSITIVE LOGITS
     her
    0.10
     separately
    0.10
    ump
    0.10
     Joined
    0.09
     largely
    0.09
     reportedly
    0.09
    rab
    0.09
     jointly
    0.08
     widespread
    0.08
     annually
    0.08
    Activations Density 0.025%

    No Known Activations