© 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. 115002
    Prev
    Next
    INDEX
    Explanations

    the [history/world/United States/country/NFL/etc.]

    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
    urses
    -0.10
    abel
    -0.08
    /documentation
    -0.07
     Duc
    -0.07
    aters
    -0.07
     purge
    -0.07
     Consort
    -0.07
    atch
    -0.07
     Winston
    -0.07
    ivo
    -0.07
    POSITIVE LOGITS
     history
    0.26
     entire
    0.22
    history
    0.21
     HISTORY
    0.19
     whole
    0.18
     History
    0.17
    History
    0.16
    _history
    0.16
     world
    0.16
    whole
    0.16
    Activations Density 0.086%

    No Known Activations