© 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. 17766
    Prev
    Next
    INDEX
    Explanations

    ancient rulers or generals

    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
     ISA
    -0.11
    éĻ¢
    -0.11
     Islamic
    -0.11
     holster
    -0.11
     Gros
    -0.10
     reli
    -0.10
     Anglic
    -0.10
     Ottoman
    -0.10
    Marks
    -0.10
     Past
    -0.10
    POSITIVE LOGITS
     Celt
    0.14
     strategist
    0.12
     Maced
    0.11
     Gaul
    0.11
     generals
    0.11
     Strateg
    0.11
     strateg
    0.11
     Spart
    0.11
     Lu
    0.10
     Liu
    0.10
    Activations Density 0.183%

    No Known Activations