© 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. 114409
    Prev
    Next
    INDEX
    Explanations

    optimize settings and performance

    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
    Mov
    -0.10
     Lal
    -0.10
     steering
    -0.09
     burst
    -0.09
    Gran
    -0.09
    hipster
    -0.09
     Mov
    -0.09
     sophistication
    -0.09
     softer
    -0.09
     Edwards
    -0.09
    POSITIVE LOGITS
     Optim
    0.13
     optimize
    0.12
     optimizing
    0.12
    Opt
    0.11
     optimization
    0.11
    /opt
    0.11
     Optimization
    0.10
     Opt
    0.10
     performance
    0.10
     simd
    0.09
    Activations Density 0.161%

    No Known Activations