© 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. 14299
    Prev
    Next
    INDEX
    Explanations

    privacy and modesty

    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
     Silent
    -0.11
     disen
    -0.10
     silently
    -0.10
     contr
    -0.10
     Flat
    -0.09
     silent
    -0.09
    Flat
    -0.09
     sess
    -0.09
     Neg
    -0.09
     Kitt
    -0.09
    POSITIVE LOGITS
     privacy
    0.22
     Privacy
    0.19
    privacy
    0.19
     embarrassed
    0.18
     decency
    0.18
     embarrassment
    0.17
     modest
    0.17
    Privacy
    0.16
     embarrassing
    0.15
     sensitive
    0.15
    Activations Density 0.153%

    No Known Activations