© 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. 4662
    Prev
    Next
    INDEX
    Explanations

    providing information and details

    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
    arlo
    -0.11
    TestMethod
    -0.10
     lifelong
    -0.10
     periodically
    -0.09
    ubb
    -0.09
     Mang
    -0.09
    ugg
    -0.09
     unnoticed
    -0.09
    icc
    -0.09
     forcibly
    -0.09
    POSITIVE LOGITS
     informative
    0.28
     informational
    0.27
     information
    0.27
     detailed
    0.25
     Detailed
    0.23
     detail
    0.23
     Information
    0.23
     informations
    0.23
    information
    0.22
    -information
    0.22
    Activations Density 0.611%

    No Known Activations