© 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. 33224
    Prev
    Next
    INDEX
    Explanations

    reference, comparison, baseline

    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
     mism
    -0.10
     secrets
    -0.10
     Explanation
    -0.10
    åįİ
    -0.09
     Brew
    -0.09
    DL
    -0.09
     invitations
    -0.09
     enticing
    -0.09
     features
    -0.08
     hij
    -0.08
    POSITIVE LOGITS
     reference
    0.40
     comparison
    0.34
     baseline
    0.34
     benchmark
    0.34
     benchmarks
    0.31
     comparator
    0.31
     Reference
    0.31
    reference
    0.31
     comparisons
    0.30
     comparative
    0.27
    Activations Density 0.604%

    No Known Activations