© 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. 25937
    Prev
    Next
    INDEX
    Explanations

    resentment of being wronged

    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
     unfortunately
    -0.12
     lightning
    -0.11
    UIS
    -0.11
     sadly
    -0.11
     pes
    -0.10
     retrieving
    -0.10
    .nc
    -0.10
     reluctantly
    -0.10
     duly
    -0.10
     Hate
    -0.10
    POSITIVE LOGITS
     trick
    0.13
     ruined
    0.12
     forcing
    0.12
     Ru
    0.12
    ru
    0.12
     priorit
    0.11
     force
    0.11
    221
    0.11
     ruin
    0.11
     jeopard
    0.10
    Activations Density 0.037%

    No Known Activations