© 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. 31696
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by action

    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
     nestled
    -0.10
     grips
    -0.09
     leaned
    -0.09
     chuckled
    -0.09
     cou
    -0.09
     leans
    -0.09
     downright
    -0.09
     scarce
    -0.08
     smiled
    -0.08
     Maybe
    -0.07
    POSITIVE LOGITS
     then
    0.32
     subsequently
    0.26
     thus
    0.25
    then
    0.25
     later
    0.24
     eventually
    0.23
     therefore
    0.23
     thereby
    0.18
     consequently
    0.17
     entonces
    0.17
    Activations Density 0.727%

    No Known Activations