© 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. 115926
    Prev
    Next
    INDEX
    Explanations

    deception, deceit, misleading, fooling

    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
     overrun
    -0.09
     escalation
    -0.09
    agi
    -0.09
     touchdown
    -0.08
     reck
    -0.08
     Gord
    -0.08
    zw
    -0.08
     intersection
    -0.08
     gum
    -0.08
     comm
    -0.08
    POSITIVE LOGITS
     dece
    0.12
     deceptive
    0.12
    /disc
    0.11
     pract
    0.11
    /man
    0.11
     tricky
    0.11
    /false
    0.11
    appa
    0.10
    ingly
    0.10
     deception
    0.10
    Activations Density 0.016%

    No Known Activations