© 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. 27828
    Prev
    Next
    INDEX
    Explanations

    secret

    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
     rond
    -0.12
     Misc
    -0.11
    bard
    -0.10
    /qu
    -0.10
     Rogue
    -0.10
     scenarios
    -0.09
     salvage
    -0.09
    stripe
    -0.09
     Worst
    -0.09
     clums
    -0.09
    POSITIVE LOGITS
     secret
    0.44
     secrets
    0.41
     Secrets
    0.34
    secret
    0.33
     Secret
    0.31
    Secret
    0.30
    -secret
    0.29
     SECRET
    0.27
    SECRET
    0.25
     secre
    0.24
    Activations Density 0.265%

    No Known Activations