© 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. 8314
    Prev
    Next
    INDEX
    Explanations

    remains of

    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
    feit
    -0.10
     Niet
    -0.09
    uran
    -0.09
    -ahead
    -0.09
     Mey
    -0.09
     blanks
    -0.09
     combinations
    -0.08
     pref
    -0.08
     nir
    -0.08
     Elliott
    -0.08
    POSITIVE LOGITS
     Hurricane
    0.11
    stub
    0.11
    istance
    0.10
     Stub
    0.10
    reas
    0.09
     collapsing
    0.09
     flowering
    0.09
     Resistance
    0.09
    loh
    0.09
     Democracy
    0.09
    Activations Density 0.004%

    No Known Activations