© 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. 26066
    Prev
    Next
    INDEX
    Explanations

    winning awards and recognition

    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
     conceal
    -0.10
     Fac
    -0.10
     surre
    -0.09
     Surre
    -0.09
     consum
    -0.09
     wiped
    -0.09
    inder
    -0.09
     Classes
    -0.08
    ubo
    -0.08
    etto
    -0.08
    POSITIVE LOGITS
     awards
    0.42
     accol
    0.36
     Awards
    0.33
     award
    0.29
     recognition
    0.27
     prizes
    0.24
     acclaim
    0.24
     Recognition
    0.24
    Recognition
    0.24
     prestigious
    0.23
    Activations Density 0.324%

    No Known Activations