© 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. 28516
    Prev
    Next
    INDEX
    Explanations

    historical conflict and revenge

    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
    reff
    -0.13
     gigg
    -0.13
     prank
    -0.12
     scare
    -0.12
     sock
    -0.12
     nicknamed
    -0.11
     gradu
    -0.11
     closet
    -0.11
     babys
    -0.11
     Clown
    -0.11
    POSITIVE LOGITS
     vengeance
    0.12
     Historical
    0.11
     historical
    0.11
    histor
    0.10
     mercy
    0.10
     wrath
    0.10
     laut
    0.10
     revenge
    0.10
     conquer
    0.09
     raping
    0.09
    Activations Density 0.010%

    No Known Activations