© 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. 89325
    Prev
    Next
    INDEX
    Explanations

    privately, secretly, internally

    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
     apparently
    -0.11
     Apparently
    -0.10
     reportedly
    -0.09
     tiers
    -0.09
     expectation
    -0.09
    Apparently
    -0.09
     yup
    -0.08
     converged
    -0.08
    angs
    -0.08
     suddenly
    -0.08
    POSITIVE LOGITS
     personally
    0.19
     Personally
    0.18
     secretly
    0.17
    Personally
    0.17
     secret
    0.14
     internally
    0.13
     privately
    0.13
     disagrees
    0.13
     silently
    0.13
    secret
    0.13
    Activations Density 0.089%

    No Known Activations