© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 92457
    Prev
    Next
    INDEX
    Explanations

    anger, rage, furious, yelling, fists

    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
    Negative Logits
     nostalg
    -0.17
     encour
    -0.14
     gigg
    -0.14
     smiling
    -0.14
     smiles
    -0.13
     cheerful
    -0.13
     reassuring
    -0.13
     shy
    -0.13
     cheering
    -0.12
     smiled
    -0.12
    POSITIVE LOGITS
     angrily
    0.50
     anger
    0.48
     angry
    0.48
     rage
    0.44
     furious
    0.37
     enraged
    0.37
     fury
    0.36
     angered
    0.36
     Angry
    0.36
     resentment
    0.35
    Activations Density 0.427%

    No Known Activations