© 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. 49920
    Prev
    Next
    INDEX
    Explanations

    royal titles and high-ranking individuals

    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
     Bills
    -0.09
    ISR
    -0.09
    uing
    -0.08
     deficit
    -0.08
    urring
    -0.08
     Zus
    -0.08
     vault
    -0.08
    kor
    -0.08
     Acts
    -0.08
     Miner
    -0.08
    POSITIVE LOGITS
     Majesty
    0.29
     maj
    0.27
     Excell
    0.25
     Maj
    0.22
     excell
    0.21
     Emin
    0.20
     High
    0.19
     Grace
    0.19
     lord
    0.18
     Lord
    0.18
    Activations Density 0.046%

    No Known Activations