© 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. 29534
    Prev
    Next
    INDEX
    Explanations

    188 108

    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
    ee
    -0.09
    rous
    -0.09
     pallet
    -0.08
    iore
    -0.08
    er
    -0.08
    fait
    -0.08
    eer
    -0.07
     Cra
    -0.07
    orate
    -0.07
    orc
    -0.07
    POSITIVE LOGITS
    andard
    0.10
    _callable
    0.10
    istem
    0.09
    ained
    0.09
     pardon
    0.09
    edly
    0.09
     colorful
    0.09
    idle
    0.09
    lob
    0.09
     temper
    0.09
    Activations Density 0.123%

    No Known Activations