© 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. 31937
    Prev
    Next
    INDEX
    Explanations

    dental procedures, health care, surgery, treatment options

    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
     neutrality
    -0.10
     disappointing
    -0.10
     incumbent
    -0.10
     disappoint
    -0.09
     unp
    -0.09
     ETA
    -0.09
    umo
    -0.09
    oodle
    -0.09
     disple
    -0.09
     bystand
    -0.09
    POSITIVE LOGITS
     resort
    0.13
     surgeries
    0.11
     untreated
    0.11
     neglected
    0.11
     incur
    0.11
     treatment
    0.11
     incurred
    0.11
     DIY
    0.11
     uninsured
    0.10
     relying
    0.10
    Activations Density 0.001%

    No Known Activations