© 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. 49925
    Prev
    Next
    INDEX
    Explanations

    verbs of writing and reporting

    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
    BE
    -0.10
     BE
    -0.10
    inte
    -0.10
     publications
    -0.10
     saying
    -0.10
     staging
    -0.10
     Saying
    -0.09
    /read
    -0.09
     publication
    -0.09
    ippi
    -0.09
    POSITIVE LOGITS
     writes
    0.17
     Writes
    0.15
     write
    0.15
    writes
    0.14
     writing
    0.14
     observes
    0.13
    writing
    0.12
     Write
    0.12
     wrote
    0.12
     approving
    0.11
    Activations Density 0.247%

    No Known Activations