© 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. 113942
    Prev
    Next
    INDEX
    Explanations

    subjects, arts, and sciences

    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
     nationalism
    -0.10
    aleb
    -0.09
     innovation
    -0.09
     patriotism
    -0.08
     secrecy
    -0.08
    endo
    -0.08
     adultery
    -0.08
     husbands
    -0.08
     gunfire
    -0.08
     pagination
    -0.08
    POSITIVE LOGITS
     outdoors
    0.21
     concept
    0.20
     subject
    0.20
     sciences
    0.17
     arts
    0.17
     topic
    0.15
     workings
    0.14
    subject
    0.14
     finer
    0.14
     joys
    0.13
    Activations Density 0.386%

    No Known Activations