© 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. 3353
    Prev
    Next
    INDEX
    Explanations

    how can i

    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
    sem
    -0.10
     pseud
    -0.09
    æĮ
    -0.09
    apr
    -0.09
     Barrett
    -0.09
    emet
    -0.08
    oud
    -0.08
     Grat
    -0.08
     potentially
    -0.08
    asty
    -0.08
    POSITIVE LOGITS
    EP
    0.10
     Required
    0.10
     Dew
    0.10
    /live
    0.10
     EP
    0.10
    aign
    0.10
     Incre
    0.09
     footh
    0.09
     Mist
    0.09
     required
    0.09
    Activations Density 0.015%

    No Known Activations