© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 30127
    Prev
    Next
    INDEX
    Explanations

    skin inflammation, irritation, reaction

    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
     Shib
    -0.10
     sho
    -0.10
     buff
    -0.10
    aign
    -0.09
     dentist
    -0.09
    pressor
    -0.08
     prefix
    -0.08
     Lou
    -0.08
     homem
    -0.08
     candy
    -0.08
    POSITIVE LOGITS
     reactions
    0.14
     rash
    0.14
     reaction
    0.13
     skin
    0.12
    skin
    0.12
    Reaction
    0.12
     itching
    0.12
    /all
    0.12
     contact
    0.11
     patches
    0.11
    Activations Density 0.128%

    No Known Activations