© 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. 5811
    Prev
    Next
    INDEX
    Explanations

    medical conditions and pain symptoms

    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
     anc
    -0.11
    enburg
    -0.11
    dal
    -0.10
    DSA
    -0.09
     useless
    -0.09
    @m
    -0.09
    ushima
    -0.09
     indiscrim
    -0.09
    cape
    -0.09
    DEX
    -0.09
    POSITIVE LOGITS
     cough
    0.15
     allergy
    0.15
     allergies
    0.14
     startled
    0.14
     sudden
    0.13
     allerg
    0.13
     allergic
    0.13
     pain
    0.12
     stomach
    0.11
     suddenly
    0.11
    Activations Density 0.057%

    No Known Activations