© 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. 26840
    Prev
    Next
    INDEX
    Explanations

    migrated or transferred

    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
    alin
    -0.12
     distant
    -0.10
     Tib
    -0.10
     intervened
    -0.10
     indul
    -0.09
     alteration
    -0.09
     Frid
    -0.09
     intervening
    -0.09
    ycl
    -0.09
     remote
    -0.08
    POSITIVE LOGITS
     migrated
    0.40
     migrate
    0.38
     migrating
    0.37
     migration
    0.34
     transferred
    0.30
     Migration
    0.30
     migr
    0.29
     migrations
    0.28
     transferring
    0.28
     transfer
    0.28
    Activations Density 1.118%

    No Known Activations