© 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. 13929
    Prev
    Next
    INDEX
    Explanations

    court, advertisement, copyright, region, draw

    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
     stutter
    -0.12
    contest
    -0.11
     dumb
    -0.11
     freak
    -0.10
     forks
    -0.10
     nerv
    -0.10
     Jew
    -0.10
     awkward
    -0.10
     screamed
    -0.10
     rave
    -0.09
    POSITIVE LOGITS
     ignored
    0.21
     ignore
    0.20
     ignores
    0.19
     respond
    0.19
     ignoring
    0.19
     responds
    0.18
     response
    0.18
     responded
    0.17
     Response
    0.17
     pity
    0.17
    Activations Density 0.053%

    No Known Activations