© 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. 34106
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

    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
    ï¼ĸ
    -0.12
    agy
    -0.11
    agi
    -0.11
     impres
    -0.11
    [vi
    -0.11
    126
    -0.11
     Bord
    -0.11
     sixth
    -0.11
    736
    -0.10
    136
    -0.10
    POSITIVE LOGITS
    257
    0.10
     Henderson
    0.10
     Vera
    0.10
    237
    0.10
    227
    0.10
     Martins
    0.10
    dehy
    0.09
    ej
    0.09
    17
    0.09
    aldo
    0.09
    Activations Density 0.068%

    No Known Activations