© 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. 15087
    Prev
    Next
    INDEX
    Explanations

    numbers followed by parentheses

    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
    (em
    -0.09
     longitud
    -0.09
     Ras
    -0.09
    yat
    -0.09
    .gg
    -0.09
     Gins
    -0.09
    opo
    -0.08
     sca
    -0.08
     reim
    -0.08
    ست
    -0.08
    POSITIVE LOGITS
    obe
    0.10
    eker
    0.10
     preamble
    0.10
    OTE
    0.10
     Evening
    0.09
     upstream
    0.09
     Cran
    0.09
     carb
    0.09
    cms
    0.09
     pt
    0.09
    Activations Density 0.004%

    No Known Activations