© 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. 4219
    Prev
    Next
    INDEX
    Explanations

    reporting opinions or statements

    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
    Ø
    -0.08
     Brew
    -0.08
    sville
    -0.08
    biz
    -0.08
     Lite
    -0.08
     Digest
    -0.07
    usa
    -0.07
     Til
    -0.07
    bage
    -0.07
     und
    -0.07
    POSITIVE LOGITS
     reply
    0.10
     Hartford
    0.10
     rasp
    0.10
     replied
    0.10
     replies
    0.10
    ikes
    0.10
     rejo
    0.10
    =?,
    0.10
     cen
    0.10
     ras
    0.10
    Activations Density 0.011%

    No Known Activations