© 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. 32607
    Prev
    Next
    INDEX
    Explanations

    highest or extreme values or ratings

    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
     moderate
    -0.19
     moderately
    -0.19
     mediocre
    -0.19
     medium
    -0.17
     Medium
    -0.17
     halfway
    -0.16
     weaker
    -0.16
    Intermediate
    -0.15
     Moderate
    -0.15
     HALF
    -0.15
    POSITIVE LOGITS
     highest
    0.20
     extreme
    0.19
    highest
    0.17
     Highest
    0.17
     ultimate
    0.17
     Extreme
    0.17
     maximal
    0.16
    Highest
    0.16
     maximum
    0.16
    Extreme
    0.15
    Activations Density 1.290%

    No Known Activations