© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 25768
    Prev
    Next
    INDEX
    Explanations

    revenge, vengeance, or retaliation

    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
     Erick
    -0.10
     Crisis
    -0.09
     crises
    -0.09
     depress
    -0.09
    ennen
    -0.09
     flutter
    -0.09
     Pra
    -0.09
     Vere
    -0.09
    èĪ
    -0.09
    inan
    -0.09
    POSITIVE LOGITS
     revenge
    0.77
     Revenge
    0.62
     vengeance
    0.62
     retaliation
    0.52
     retali
    0.49
    venge
    0.48
     retal
    0.47
     vind
    0.37
     repay
    0.34
     punish
    0.33
    Activations Density 0.235%

    No Known Activations