© 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. 24965
    Prev
    Next
    INDEX
    Explanations

    such as / like

    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
    ogh
    -0.08
     whatever
    -0.07
    mighty
    -0.07
    zee
    -0.07
     Kil
    -0.07
    gee
    -0.07
    aec
    -0.07
    pants
    -0.07
    itm
    -0.07
    ece
    -0.07
    POSITIVE LOGITS
     ours
    0.15
     ones
    0.14
     namely
    0.14
     etwa
    0.14
     notably
    0.13
    ä¾ĭå¦Ĥ
    0.12
    such
    0.12
     moons
    0.11
     such
    0.11
     ie
    0.11
    Activations Density 0.670%

    No Known Activations