© 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. 25882
    Prev
    Next
    INDEX
    Explanations

    using electronic devices and services

    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
     goals
    -0.09
     pregnancies
    -0.08
     projects
    -0.08
     pursuits
    -0.08
     conversations
    -0.08
     discussions
    -0.08
    ueva
    -0.08
    als
    -0.08
     experiments
    -0.08
    */
    -0.07
    POSITIVE LOGITS
     tools
    0.23
     techniques
    0.21
     resources
    0.20
     tactics
    0.18
     methods
    0.17
     funds
    0.16
     technique
    0.16
    tools
    0.16
     tool
    0.15
    ertools
    0.15
    Activations Density 1.130%

    No Known Activations