© 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. 29668
    Prev
    Next
    INDEX
    Explanations

    if you have

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Fres
    -0.11
    egin
    -0.11
    ohl
    -0.10
    248
    -0.10
    Sup
    -0.10
    resh
    -0.10
    iej
    -0.10
    redi
    -0.10
    lets
    -0.09
     BUT
    -0.09
    POSITIVE LOGITS
    åĪĻ
    0.16
     additionally
    0.15
     additional
    0.13
    ï¼ĮåĪĻ
    0.12
     obviously
    0.12
     dit
    0.12
     even
    0.11
     similarly
    0.11
     doubly
    0.10
     ÑĤо
    0.10
    Activations Density 0.393%

    No Known Activations