© 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. 28342
    Prev
    Next
    INDEX
    Explanations

    cycles and routines

    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
     kne
    -0.09
     disproportion
    -0.09
     Prote
    -0.08
    Vault
    -0.08
    hung
    -0.08
    utral
    -0.08
    Opts
    -0.08
     cray
    -0.08
    Paste
    -0.08
     Deng
    -0.08
    POSITIVE LOGITS
     rut
    0.21
     routine
    0.18
     cycle
    0.18
     routines
    0.17
     cycles
    0.17
    rut
    0.17
     trap
    0.15
    cycle
    0.15
     Rut
    0.15
     groove
    0.15
    Activations Density 0.041%

    No Known Activations