© 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. 89672
    Prev
    Next
    INDEX
    Explanations

    -ology or -ography words

    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
    sville
    -0.12
    rica
    -0.12
    ings
    -0.12
    ness
    -0.11
    ed
    -0.11
    edly
    -0.10
    amento
    -0.10
    ement
    -0.10
     Technologies
    -0.10
    ships
    -0.10
    POSITIVE LOGITS
    ALLY
    0.16
    ically
    0.14
    ën
    0.14
    ally
    0.12
     buffs
    0.12
    иÑĩеÑģ
    0.11
    -driven
    0.11
    cal
    0.10
    -based
    0.10
    -inspired
    0.10
    Activations Density 0.725%

    No Known Activations