© 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. 87637
    Prev
    Next
    INDEX
    Explanations

    "will exemplify"

    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
    ber
    -0.09
     Tout
    -0.08
     Kitt
    -0.08
    lush
    -0.07
     anger
    -0.07
    /fa
    -0.07
     Darkness
    -0.06
     eux
    -0.06
     foul
    -0.06
     Him
    -0.06
    POSITIVE LOGITS
     veter
    0.11
    noc
    0.11
     notoriously
    0.11
     undocumented
    0.11
    eos
    0.10
    opp
    0.10
     interiors
    0.10
    vely
    0.10
     Alexand
    0.10
     outnumber
    0.10
    Activations Density 0.270%

    No Known Activations