© 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. 89101
    Prev
    Next
    INDEX
    Explanations

    as of date

    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
     Ziel
    -0.11
     Mull
    -0.10
     Brit
    -0.09
     Kov
    -0.09
    izzie
    -0.09
     Ethics
    -0.09
     Pell
    -0.09
    aco
    -0.09
    INU
    -0.09
    elson
    -0.09
    POSITIVE LOGITS
     orphan
    0.09
     couple
    0.08
     Dorm
    0.08
    apo
    0.08
     Hall
    0.08
     loose
    0.08
     Couple
    0.08
    angan
    0.08
     cutoff
    0.08
     met
    0.08
    Activations Density 0.006%

    No Known Activations