© 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. 17202
    Prev
    Next
    INDEX
    Explanations

    best

    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
    omo
    -0.10
     Conrad
    -0.09
     aut
    -0.09
    zik
    -0.09
     SUR
    -0.09
    bach
    -0.09
     gained
    -0.08
     weight
    -0.08
    odash
    -0.08
     bach
    -0.08
    POSITIVE LOGITS
    -best
    0.31
     best
    0.31
     Best
    0.31
     excellence
    0.30
     goodness
    0.30
    best
    0.30
    (best
    0.29
    Best
    0.29
     better
    0.28
     good
    0.28
    Activations Density 0.299%

    No Known Activations