© 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. 29254
    Prev
    Next
    INDEX
    Explanations

    't 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
    uhan
    -0.09
     lamin
    -0.08
     Pist
    -0.08
     Koh
    -0.07
     Lam
    -0.07
     mec
    -0.07
     Capital
    -0.07
    igu
    -0.07
     unfore
    -0.07
     CHE
    -0.07
    POSITIVE LOGITS
     expecting
    0.11
     Dre
    0.11
     Singer
    0.11
     tit
    0.10
     recognise
    0.10
     Wilkinson
    0.10
     meant
    0.10
    cka
    0.10
     recognize
    0.10
     Bowling
    0.10
    Activations Density 0.028%

    No Known Activations