© 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. 48737
    Prev
    Next
    INDEX
    Explanations

    bone and collagen health

    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
     blindly
    -0.09
     blind
    -0.09
    series
    -0.09
    dirty
    -0.09
     digestive
    -0.08
     illeg
    -0.08
    rite
    -0.08
    éĮ
    -0.08
    hole
    -0.08
    erro
    -0.08
    POSITIVE LOGITS
     insufficient
    0.13
     hydration
    0.13
     Ade
    0.12
     collagen
    0.12
     inadequate
    0.12
     moistur
    0.12
     absorbing
    0.12
     hydrated
    0.12
     spontaneous
    0.11
     sufficient
    0.11
    Activations Density 0.227%

    No Known Activations