© 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. 46227
    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
    管
    -0.09
    inel
    -0.08
     doesnt
    -0.08
    eros
    -0.08
     behold
    -0.07
    inos
    -0.07
     Revel
    -0.07
     consolation
    -0.07
     succes
    -0.07
     handed
    -0.07
    POSITIVE LOGITS
    /lg
    0.12
     sucker
    0.12
    /Dk
    0.11
    erce
    0.11
    IFn
    0.11
    ,âĢ¦↵↵
    0.10
    Slf
    0.10
     Weaver
    0.10
    -horizontal
    0.10
    ))==
    0.10
    Activations Density 0.007%

    No Known Activations