© 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. 14530
    Prev
    Next
    INDEX
    Explanations

    speech attribution verbs

    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
    ensi
    -0.10
     ve
    -0.10
     minority
    -0.10
    .'_
    -0.09
    pill
    -0.09
     dun
    -0.09
     remed
    -0.09
    vé
    -0.09
     amb
    -0.09
     Arabs
    -0.09
    POSITIVE LOGITS
     said
    0.26
     says
    0.25
     saying
    0.25
     Says
    0.24
     exclaimed
    0.22
     Said
    0.22
    说
    0.21
    said
    0.20
     replied
    0.20
    says
    0.19
    Activations Density 0.281%

    No Known Activations