© 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. 113657
    Prev
    Next
    INDEX
    Explanations

    process or industry

    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
     lineup
    -0.09
    ATTER
    -0.08
    lint
    -0.08
    ilton
    -0.08
     substantive
    -0.08
    gis
    -0.08
     lassen
    -0.08
     Kenneth
    -0.08
     Fel
    -0.08
     Ire
    -0.08
    POSITIVE LOGITS
     territory
    0.15
     unavoidable
    0.12
    iche
    0.12
     nature
    0.11
     being
    0.11
    being
    0.11
     unfortunate
    0.11
    ona
    0.11
     deal
    0.11
    ieu
    0.11
    Activations Density 0.066%

    No Known Activations