© 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. 91399
    Prev
    Next
    INDEX
    Explanations

    citation markers

    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
     declar
    -0.10
     UPC
    -0.10
     icy
    -0.10
     blasting
    -0.09
    ÃŃc
    -0.09
     freezing
    -0.09
     explan
    -0.09
    oric
    -0.09
     impost
    -0.09
    YZ
    -0.09
    POSITIVE LOGITS
    itra
    0.10
     Aires
    0.10
     branch
    0.09
     Prem
    0.09
     profiling
    0.09
     dil
    0.09
    irá
    0.09
     pioneering
    0.09
    ched
    0.09
     race
    0.09
    Activations Density 0.018%

    No Known Activations