© 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. 25821
    Prev
    Next
    INDEX
    Explanations

    lie, lies, lying, lied

    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
    tones
    -0.11
     hij
    -0.10
    uste
    -0.10
    idot
    -0.10
    ص
    -0.10
    /fr
    -0.09
     hitch
    -0.09
    arde
    -0.09
     Zum
    -0.09
     lightly
    -0.09
    POSITIVE LOGITS
     lies
    0.15
     lie
    0.12
    Lie
    0.12
     lying
    0.11
     Lie
    0.11
     lied
    0.11
     omission
    0.11
     falsehood
    0.10
    lie
    0.10
     oath
    0.09
    Activations Density 0.034%

    No Known Activations