© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 117568
    Prev
    Next
    INDEX
    Explanations

    usage and techniques

    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
    Negative Logits
    _tools
    -0.12
    indr
    -0.12
     Tools
    -0.11
     tools
    -0.11
    SHA
    -0.11
     Protect
    -0.10
     sift
    -0.10
    TOOLS
    -0.10
     consolidate
    -0.10
     consolidation
    -0.10
    POSITIVE LOGITS
     usage
    0.38
     Usage
    0.33
    Usage
    0.29
    usage
    0.28
    _usage
    0.27
     misuse
    0.27
     USAGE
    0.24
    USAGE
    0.22
    .usage
    0.19
     use
    0.19
    Activations Density 0.430%

    No Known Activations