© 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. 46134
    Prev
    Next
    INDEX
    Explanations

    together

    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
     together
    -0.11
     collectively
    -0.10
     cup
    -0.08
     between
    -0.08
    sten
    -0.08
     individually
    -0.08
     alike
    -0.08
     Cup
    -0.07
    wart
    -0.07
    cup
    -0.07
    POSITIVE LOGITS
    .nih
    0.12
     Armstrong
    0.11
    /Dk
    0.11
     Bri
    0.11
    /cs
    0.11
     xo
    0.11
    ||↵
    0.10
     Chad
    0.10
     Ashley
    0.10
     Swinger
    0.10
    Activations Density 0.015%

    No Known Activations