© 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. 25007
    Prev
    Next
    INDEX
    Explanations

    saturated

    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
    essa
    -0.11
    assen
    -0.10
    otti
    -0.10
    ouro
    -0.10
    embro
    -0.10
     spoiled
    -0.10
    nel
    -0.10
     sou
    -0.10
    ohana
    -0.09
    pol
    -0.09
    POSITIVE LOGITS
    /run
    0.09
     completely
    0.08
     complet
    0.08
     Thom
    0.08
    /bl
    0.08
    utral
    0.07
    icorn
    0.07
    -up
    0.07
     kap
    0.07
    /dr
    0.07
    Activations Density 0.008%

    No Known Activations