© 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. 89893
    Prev
    Next
    INDEX
    Explanations

    questions about conditions

    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
     Nay
    -0.09
     unseen
    -0.09
    stakes
    -0.09
     squarely
    -0.09
     Dund
    -0.08
    bjerg
    -0.08
    etre
    -0.08
    .sky
    -0.08
     ain
    -0.08
     unthinkable
    -0.08
    POSITIVE LOGITS
     ever
    0.18
     anymore
    0.14
     EVER
    0.13
     necessarily
    0.13
     still
    0.13
     Ever
    0.12
     Really
    0.12
     HAVE
    0.11
    bew
    0.11
    Exist
    0.11
    Activations Density 0.160%

    No Known Activations