© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 15939
    Prev
    Next
    INDEX
    Explanations

    job searching and application 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
     confession
    -0.11
     confess
    -0.10
     prepar
    -0.09
     preparations
    -0.09
     Dul
    -0.09
     Clement
    -0.08
    /form
    -0.08
     Info
    -0.08
    Filed
    -0.08
     compos
    -0.08
    POSITIVE LOGITS
     periodic
    0.11
     periodically
    0.11
     Rosenstein
    0.10
    -monitor
    0.10
    .waitKey
    0.10
     monitoring
    0.10
     Nail
    0.10
    odem
    0.10
     Monitoring
    0.10
     selectively
    0.10
    Activations Density 0.204%

    No Known Activations