© 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. 50900
    Prev
    Next
    INDEX
    Explanations

    names ending in ana/ara/ada/ama

    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
     chap
    -0.10
     incom
    -0.09
    illing
    -0.09
     unthinkable
    -0.09
     precise
    -0.09
    zed
    -0.09
    OH
    -0.08
     civil
    -0.08
    ughters
    -0.08
     critically
    -0.08
    POSITIVE LOGITS
    e
    0.16
    a
    0.13
    auc
    0.11
    eel
    0.10
    o
    0.10
    ea
    0.10
    pta
    0.10
    eus
    0.10
    anni
    0.09
     barring
    0.09
    Activations Density 0.152%

    No Known Activations