© 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. 16473
    Prev
    Next
    INDEX
    Explanations

    looking back and realising

    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
     meanwhile
    -0.11
    ););↵
    -0.10
     backstage
    -0.10
     unavailable
    -0.10
     unheard
    -0.10
     EOF
    -0.10
     rumored
    -0.09
    ulla
    -0.09
     Pear
    -0.09
     recon
    -0.09
    POSITIVE LOGITS
     similarities
    0.12
     actually
    0.11
     clearly
    0.11
     really
    0.11
     indeed
    0.11
     pretty
    0.11
    actually
    0.10
     inconsistencies
    0.10
     conclusion
    0.10
     consist
    0.10
    Activations Density 0.309%

    No Known Activations