© 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. 114869
    Prev
    Next
    INDEX
    Explanations

    will, would, or 'll

    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
    was
    -0.13
    Was
    -0.11
    iams
    -0.11
     nós
    -0.11
     bog
    -0.11
    agit
    -0.11
    ennent
    -0.11
    RIX
    -0.10
    ’ve
    -0.10
    aye
    -0.10
    POSITIVE LOGITS
     will
    0.48
    will
    0.36
     WILL
    0.34
    ä¼ļ
    0.32
    'll
    0.29
    ’ll
    0.28
     wil
    0.26
     won
    0.26
     akan
    0.25
     бÑĥдеÑĤ
    0.25
    Activations Density 0.670%

    No Known Activations