© 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. 92079
    Prev
    Next
    INDEX
    Explanations

    forcing, compelling, or urging 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
     Proud
    -0.11
     congrat
    -0.11
     apologized
    -0.11
     Williamson
    -0.10
     acknow
    -0.10
    chalk
    -0.10
     Feedback
    -0.10
     stabilized
    -0.10
     congratulate
    -0.10
     panor
    -0.10
    POSITIVE LOGITS
     persuasion
    0.28
     coax
    0.28
     persuasive
    0.28
     persu
    0.25
     insist
    0.23
     persuade
    0.22
     compel
    0.22
     forcibly
    0.22
     insistence
    0.22
     urging
    0.22
    Activations Density 0.098%

    No Known Activations