© 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. 15741
    Prev
    Next
    INDEX
    Explanations

    talking about things

    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
     please
    -0.08
    uding
    -0.08
    ornings
    -0.08
     tir
    -0.08
     involuntary
    -0.07
     taped
    -0.07
     Ebony
    -0.07
    273
    -0.07
     lik
    -0.07
     subt
    -0.07
    POSITIVE LOGITS
     yesterday
    0.12
     unrelated
    0.12
     recent
    0.12
     upcoming
    0.12
     earlier
    0.11
    recent
    0.11
     plans
    0.11
     recap
    0.11
     previous
    0.11
     random
    0.11
    Activations Density 0.020%

    No Known Activations