© 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. 88300
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

    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
     tro
    -0.10
     Parker
    -0.09
     prem
    -0.09
    è±
    -0.09
     Gates
    -0.09
     Werner
    -0.09
    apa
    -0.08
    icket
    -0.08
     continuation
    -0.08
     proton
    -0.08
    POSITIVE LOGITS
    MAS
    0.09
     stamp
    0.09
     none
    0.09
     Mercedes
    0.08
    eras
    0.08
     NONE
    0.08
    ·»
    0.08
     tightening
    0.08
    veau
    0.08
    elen
    0.08
    Activations Density 1.901%

    No Known Activations