© 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. 28652
    Prev
    Next
    INDEX
    Explanations

    secret show, sale, romance, Service, hidden character

    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
     deport
    -0.07
     Debbie
    -0.07
    iver
    -0.07
    izer
    -0.06
    /articles
    -0.06
    Article
    -0.06
     Neal
    -0.06
    isers
    -0.06
    rollo
    -0.06
     bri
    -0.06
    POSITIVE LOGITS
     secretly
    0.22
     secret
    0.20
     hidden
    0.19
     clandest
    0.17
    -secret
    0.17
     Hidden
    0.17
     secrets
    0.17
    secret
    0.17
     sne
    0.16
     Secret
    0.16
    Activations Density 0.002%

    No Known Activations