© 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. 47848
    Prev
    Next
    INDEX
    Explanations

    can or could followed by a verb

    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
     succesfully
    -0.10
     Hud
    -0.10
    wolf
    -0.10
     remember
    -0.10
     Anast
    -0.10
     inund
    -0.09
    aldo
    -0.09
    atori
    -0.09
     successfully
    -0.09
     Uns
    -0.09
    POSITIVE LOGITS
     only
    0.11
     ONLY
    0.10
    otto
    0.10
    sted
    0.09
    't
    0.09
    iola
    0.09
    imas
    0.09
    .ser
    0.09
     Only
    0.09
     corrupt
    0.09
    Activations Density 0.071%

    No Known Activations