© 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. 5750
    Prev
    Next
    INDEX
    Explanations

    covert actions and secrecy

    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
     strut
    -0.12
    {:
    -0.10
    Ĥ¬
    -0.10
    bows
    -0.10
    avana
    -0.10
     bows
    -0.10
     formally
    -0.10
     barr
    -0.10
    613
    -0.10
     Maker
    -0.10
    POSITIVE LOGITS
     secretly
    0.30
     surre
    0.27
     covert
    0.25
     sneak
    0.24
     discreet
    0.23
     subtly
    0.23
     stealth
    0.23
     quietly
    0.20
     sne
    0.18
     unnoticed
    0.18
    Activations Density 0.054%

    No Known Activations