© 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. 4110
    Prev
    Next
    INDEX
    Explanations

    upset or angry words

    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
     foss
    -0.10
     Chall
    -0.09
    asso
    -0.09
     Prefer
    -0.09
     constr
    -0.09
     pit
    -0.09
     Nope
    -0.08
    beck
    -0.08
     circ
    -0.08
     Obl
    -0.08
    POSITIVE LOGITS
     revenge
    0.19
     rage
    0.18
     anger
    0.17
     retali
    0.17
     retal
    0.17
     Revenge
    0.15
     vengeance
    0.14
     retaliation
    0.14
     angry
    0.13
     fury
    0.13
    Activations Density 0.004%

    No Known Activations