© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 112292
    Prev
    Next
    INDEX
    Explanations

    fairly decent rating

    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
     unparalleled
    -0.11
     irresistible
    -0.11
     priceless
    -0.11
     genius
    -0.10
     incredible
    -0.10
     unforgettable
    -0.10
     magically
    -0.10
    Wow
    -0.10
     Wow
    -0.10
     wow
    -0.09
    POSITIVE LOGITS
     decent
    0.45
     moderately
    0.40
     mediocre
    0.37
     reasonably
    0.35
     fairly
    0.33
     moderate
    0.33
     respectable
    0.28
     okay
    0.28
     reasonable
    0.27
     relatively
    0.26
    Activations Density 0.476%

    No Known Activations