© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 91212
    Prev
    Next
    INDEX
    Explanations

    Roman history and figures

    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
     Saud
    -0.11
     Aval
    -0.10
     Sultan
    -0.10
     Kare
    -0.09
     Louisville
    -0.09
     jal
    -0.09
     Erl
    -0.08
     Archbishop
    -0.08
    BCM
    -0.08
     Bey
    -0.08
    POSITIVE LOGITS
     Roman
    0.39
    Roman
    0.34
     Rome
    0.33
     Romans
    0.33
     Pompe
    0.30
     Caesar
    0.28
     roman
    0.28
     Nero
    0.26
     Marcus
    0.25
     Julius
    0.25
    Activations Density 0.578%

    No Known Activations