© 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. 115892
    Prev
    Next
    INDEX
    Explanations

    update and renovation

    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
    /cop
    -0.11
    /version
    -0.11
     subpo
    -0.10
     deflate
    -0.10
     Placement
    -0.09
     adjusted
    -0.09
    SETTINGS
    -0.09
     Tester
    -0.09
     syncing
    -0.09
     Protector
    -0.09
    POSITIVE LOGITS
     renovation
    0.41
     renovations
    0.38
     renov
    0.38
     remodel
    0.37
     remodeling
    0.36
     makeover
    0.32
     refurb
    0.32
     renovated
    0.31
     redesign
    0.26
     rebuild
    0.25
    Activations Density 0.674%

    No Known Activations