© 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. 90679
    Prev
    Next
    INDEX
    Explanations

    any opportunity

    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
    ENTS
    -0.10
     comparatively
    -0.10
     Plenty
    -0.10
     Vulcan
    -0.10
    pect
    -0.10
    pter
    -0.09
    asia
    -0.09
    adan
    -0.09
     Lotus
    -0.09
    inary
    -0.09
    POSITIVE LOGITS
     whenever
    0.18
     Whenever
    0.15
     wherever
    0.14
     ASAP
    0.12
    Whenever
    0.12
     opport
    0.12
     gladly
    0.11
     opportunities
    0.11
     opportunity
    0.10
     preferably
    0.10
    Activations Density 0.094%

    No Known Activations