© 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. 115679
    Prev
    Next
    INDEX
    Explanations

    accuracy trade, -American Chamber, Italian border, fluid barrier, -American University

    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
    347
    -0.08
     Blacks
    -0.07
    ubo
    -0.07
    (formatter
    -0.07
     Schwartz
    -0.07
     wand
    -0.07
     McCarthy
    -0.06
    itti
    -0.06
    zu
    -0.06
    Screens
    -0.06
    POSITIVE LOGITS
     combo
    0.28
     combination
    0.24
     combos
    0.23
     hybrid
    0.22
     ratio
    0.22
     Combo
    0.22
     hybrids
    0.22
     pair
    0.19
     combinations
    0.19
    combination
    0.19
    Activations Density 1.485%

    No Known Activations