© 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. 27289
    Prev
    Next
    INDEX
    Explanations

    pronouns and roles followed by actions

    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
    GIN
    -0.09
    oron
    -0.09
    ä»ĺ
    -0.09
    chn
    -0.09
    /styles
    -0.08
    dess
    -0.08
     respect
    -0.08
    Kenn
    -0.08
    elp
    -0.08
    hn
    -0.08
    POSITIVE LOGITS
     chiefly
    0.12
     principally
    0.12
     Lem
    0.11
     mainly
    0.11
     primarily
    0.10
     tasked
    0.10
    bred
    0.10
     merely
    0.10
    adero
    0.10
    itta
    0.09
    Activations Density 0.940%

    No Known Activations