© 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. 32085
    Prev
    Next
    INDEX
    Explanations

    presidential or ministerial titles

    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
     COVID
    -0.30
    COVID
    -0.29
     Covid
    -0.28
     covid
    -0.28
     Coronavirus
    -0.24
     coronavirus
    -0.24
     pandemic
    -0.21
     lockdown
    -0.20
     Corona
    -0.18
     quarantine
    -0.16
    POSITIVE LOGITS
     gener
    0.13
     Claude
    0.12
    itant
    0.11
     Kramer
    0.11
     Eigen
    0.11
    agi
    0.11
     slugg
    0.11
    Gener
    0.10
    http
    0.10
    iego
    0.10
    Activations Density 0.502%

    No Known Activations