© 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. 13964
    Prev
    Next
    INDEX
    Explanations

    May dates

    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
     winter
    -0.10
    uale
    -0.10
     pitch
    -0.10
    rieve
    -0.09
     Winter
    -0.09
     dich
    -0.09
    utra
    -0.09
    ALLY
    -0.09
     fingers
    -0.09
    adden
    -0.08
    POSITIVE LOGITS
    -Jun
    0.15
    ıs
    0.14
    -May
    0.13
    nard
    0.13
    份
    0.12
    day
    0.11
    -J
    0.11
    May
    0.11
    Jun
    0.10
    flower
    0.10
    Activations Density 0.059%

    No Known Activations