© 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. 89401
    Prev
    Next
    INDEX
    Explanations

    local news, elections, safety, and municipality

    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
    erais
    -0.11
    PMC
    -0.10
     Baxter
    -0.10
     tracked
    -0.10
    Convention
    -0.10
    kah
    -0.10
    ores
    -0.10
     Laud
    -0.09
     Shelf
    -0.09
    Messenger
    -0.09
    POSITIVE LOGITS
     activism
    0.10
    issan
    0.09
    ikit
    0.09
    mys
    0.08
     fract
    0.08
     effort
    0.08
    ubber
    0.08
     everlasting
    0.08
    DEN
    0.08
     perspectives
    0.08
    Activations Density 0.005%

    No Known Activations