© 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. 6876
    Prev
    Next
    INDEX
    Explanations

    usage of devices or items

    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
    -turned
    -0.08
    aic
    -0.08
    agra
    -0.08
    faction
    -0.08
     ancestor
    -0.08
     hairs
    -0.08
    apis
    -0.08
    zt
    -0.08
     resemblance
    -0.08
     fil
    -0.08
    POSITIVE LOGITS
     usage
    0.27
     Usage
    0.19
    usage
    0.19
    _usage
    0.18
     misuse
    0.18
    Usage
    0.17
     insertion
    0.16
     utilization
    0.15
     use
    0.15
     USAGE
    0.15
    Activations Density 0.071%

    No Known Activations