© 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. 88937
    Prev
    Next
    INDEX
    Explanations

    clothing or data structures

    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
    Programming
    -0.12
     Perc
    -0.12
    anova
    -0.11
    erp
    -0.11
    /misc
    -0.11
     Programming
    -0.10
     mys
    -0.10
     Gavin
    -0.10
     pretended
    -0.10
     Shaft
    -0.10
    POSITIVE LOGITS
     visible
    0.10
    lette
    0.09
     featuring
    0.08
     Visible
    0.08
     hugs
    0.08
    visible
    0.08
     installed
    0.08
     vis
    0.08
     confines
    0.07
     worn
    0.07
    Activations Density 0.023%

    No Known Activations