© 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. 18274
    Prev
    Next
    INDEX
    Explanations

    change in rate or growth

    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
     rut
    -0.09
     evolved
    -0.08
    ech
    -0.08
     Mane
    -0.08
     Shan
    -0.08
    bnb
    -0.08
    isp
    -0.08
    idis
    -0.08
     Bian
    -0.08
     concessions
    -0.08
    POSITIVE LOGITS
     accelerated
    0.31
     rate
    0.29
     faster
    0.26
     accelerate
    0.26
     slower
    0.26
     Rate
    0.26
     accelerating
    0.25
     rapid
    0.24
     acceleration
    0.24
     Acceler
    0.24
    Activations Density 0.968%

    No Known Activations