© 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. 115527
    Prev
    Next
    INDEX
    Explanations

    F. followed by number or .R, .Open, .Judicial, .District

    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
    ìĽ
    -0.11
    elas
    -0.10
     subs
    -0.10
     continent
    -0.09
     properly
    -0.09
    bk
    -0.09
     Modal
    -0.09
     redundant
    -0.09
     accountable
    -0.09
    continent
    -0.09
    POSITIVE LOGITS
    enu
    0.11
    °F
    0.11
    eries
    0.09
     fever
    0.09
    iq
    0.09
     percentile
    0.09
     proof
    0.09
    ogn
    0.09
    /dashboard
    0.09
     Frost
    0.09
    Activations Density 0.801%

    No Known Activations