© 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. 50887
    Prev
    Next
    INDEX
    Explanations

    parody, satire, imitation

    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
     Validator
    -0.10
     assort
    -0.10
     broadcasting
    -0.09
     conducive
    -0.09
    ~~~~~~~~
    -0.09
     tattoo
    -0.09
     RANDOM
    -0.09
     flagged
    -0.09
    otts
    -0.09
    actable
    -0.09
    POSITIVE LOGITS
     parody
    0.44
     spoof
    0.34
     reinterpret
    0.30
     homage
    0.26
     imitation
    0.25
     mash
    0.25
     tribute
    0.23
     satire
    0.22
     mockery
    0.21
     mock
    0.21
    Activations Density 0.708%

    No Known Activations