© 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. 5874
    Prev
    Next
    INDEX
    Explanations

    election dates

    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
     Mai
    -0.12
     Fay
    -0.11
     Maur
    -0.10
     HOWEVER
    -0.10
     Hull
    -0.10
    !!!!!
    -0.10
     Drake
    -0.10
     Roc
    -0.10
     Hawkins
    -0.10
     Toll
    -0.10
    POSITIVE LOGITS
     despite
    0.11
     lest
    0.10
    è
    0.08
     Att
    0.08
    arring
    0.08
    325
    0.08
    ahan
    0.07
     but
    0.07
     due
    0.07
    ä¸
    0.07
    Activations Density 1.428%

    No Known Activations