© 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. 113323
    Prev
    Next
    INDEX
    Explanations

    step transfer lifting moves ferry

    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
     Cone
    -0.11
     repair
    -0.10
    antis
    -0.10
     antis
    -0.10
     adj
    -0.09
     Comfort
    -0.09
     Repair
    -0.09
     Seymour
    -0.09
     vending
    -0.09
    iced
    -0.09
    POSITIVE LOGITS
     step
    0.15
    -step
    0.14
    transfer
    0.13
     transfer
    0.13
     transitional
    0.13
     stepping
    0.13
    .step
    0.13
    -transfer
    0.13
     transferring
    0.13
     transition
    0.12
    Activations Density 0.050%

    No Known Activations