© 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. 18528
    Prev
    Next
    INDEX
    Explanations

    options, love, latitude, time, clear, secrets

    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
     -(
    -0.08
     -
    -0.07
     GIT
    -0.07
     Hunter
    -0.06
    -(
    -0.06
    ——
    -0.06
     (
    -0.06
     LG
    -0.06
     practically
    -0.06
    ----
    -0.06
    POSITIVE LOGITS
     slightest
    0.15
    ,!
    0.14
    been
    0.13
    lot
    0.12
     least
    0.12
    bout
    0.12
     franca
    0.12
    äºİ
    0.12
     been
    0.12
     own
    0.12
    Activations Density 0.390%

    No Known Activations