© 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. 48160
    Prev
    Next
    INDEX
    Explanations

    international politics geopolitics history

    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
     heterosexual
    -0.15
     sex
    -0.13
     homophobic
    -0.13
     homosexuality
    -0.12
     Sex
    -0.12
     libertine
    -0.12
     scandal
    -0.12
     homosexual
    -0.12
    sexual
    -0.12
    isex
    -0.12
    POSITIVE LOGITS
     geo
    0.14
     geopol
    0.13
     geopolitical
    0.13
    geo
    0.11
     Euras
    0.11
     Geo
    0.11
     histor
    0.11
     interstate
    0.10
     Pax
    0.10
     Huntington
    0.10
    Activations Density 3.468%

    No Known Activations