© 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. 25867
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by modal 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
     happ
    -0.10
     brilliantly
    -0.09
    (am
    -0.09
     puzzled
    -0.09
    tell
    -0.09
     marvel
    -0.09
     dep
    -0.09
     worth
    -0.09
     instruct
    -0.09
     incred
    -0.09
    POSITIVE LOGITS
     shouldn
    0.25
     should
    0.21
     ought
    0.19
     Should
    0.18
    should
    0.17
    Should
    0.15
     surely
    0.15
     probably
    0.13
    .should
    0.13
    åºĶ
    0.13
    Activations Density 0.031%

    No Known Activations