© 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. 17347
    Prev
    Next
    INDEX
    Explanations

    epidemiology

    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
     invol
    -0.10
    aned
    -0.10
    issement
    -0.09
    ÑĥÑİÑī
    -0.09
    /simple
    -0.09
    /apt
    -0.09
     Vincent
    -0.09
    rous
    -0.08
    /dist
    -0.08
    .UnitTesting
    -0.08
    POSITIVE LOGITS
    ological
    0.25
    ologically
    0.21
    ologists
    0.17
    ology
    0.17
    ically
    0.16
    ologic
    0.16
    logical
    0.15
    ologist
    0.15
    chemical
    0.15
    istically
    0.13
    Activations Density 1.016%

    No Known Activations