© 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. 3490
    Prev
    Next
    INDEX
    Explanations

    Morris

    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
     strikes
    -0.11
    isy
    -0.10
    itÃł
    -0.09
     strike
    -0.09
    itative
    -0.09
    ities
    -0.09
    itta
    -0.08
     deserving
    -0.08
     Strike
    -0.08
    Spoiler
    -0.08
    POSITIVE LOGITS
    roe
    0.11
    oire
    0.09
     sidew
    0.09
    woord
    0.09
    seau
    0.09
    Sink
    0.09
    sey
    0.09
     dab
    0.09
     emot
    0.09
    Comfort
    0.09
    Activations Density 0.012%

    No Known Activations