© 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. 16267
    Prev
    Next
    INDEX
    Explanations

    ranking criteria

    np_acts-logits-general · gemini-2.5-flash-lite

    rankings, awards, and formal evaluations of institutions or entities.

    oai_token-act-pair · claude-4-5-haikuTriggered by @cam
    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
    inal
    -0.09
     Miranda
    -0.09
     inspirational
    -0.09
     attracted
    -0.08
     crossword
    -0.08
     Samar
    -0.08
     stamped
    -0.08
     attraction
    -0.08
    zet
    -0.08
     supp
    -0.08
    POSITIVE LOGITS
     criteria
    0.61
     Criteria
    0.55
     criterion
    0.50
    Criteria
    0.47
    criteria
    0.46
     criter
    0.45
     Criterion
    0.38
    _criteria
    0.36
    Criterion
    0.34
     metrics
    0.33
    Activations Density 1.381%

    No Known Activations