© 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. 7483
    Prev
    Next
    INDEX
    Explanations

    betrayal or treason

    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
     Interstate
    -0.11
    porno
    -0.11
     interstate
    -0.11
     unmarried
    -0.10
     Aura
    -0.10
     aura
    -0.10
     indiv
    -0.10
     eccentric
    -0.10
     queried
    -0.10
     Offensive
    -0.10
    POSITIVE LOGITS
     betray
    0.57
     betrayal
    0.54
     betrayed
    0.52
     betr
    0.39
     trait
    0.34
     treason
    0.28
    trait
    0.27
     Bet
    0.24
     loyalty
    0.23
     tre
    0.22
    Activations Density 0.378%

    No Known Activations