© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 112349
    Prev
    Next
    INDEX
    Explanations

    years and numbers

    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
    Not in Any Lists

    No Comments

    Negative Logits
    /on
    -0.08
    &display
    -0.08
     Seeder
    -0.08
    NSE
    -0.08
     SPA
    -0.08
     Backpack
    -0.08
     onsite
    -0.08
    COPE
    -0.08
    Blo
    -0.08
    razier
    -0.08
    POSITIVE LOGITS
    /I
    0.22
    (IR
    0.19
     IW
    0.18
    (IL
    0.18
    (IB
    0.17
    $I
    0.17
    EIF
    0.16
    (IS
    0.16
     IB
    0.16
     IH
    0.15
    Activations Density 3.347%

    No Known Activations