© 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. 90817
    Prev
    Next
    INDEX
    Explanations

    busy, hectic, overloaded

    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
     unaffected
    -0.11
     Tor
    -0.10
    haft
    -0.10
     Mog
    -0.10
     anomal
    -0.10
     insensitive
    -0.09
     Dim
    -0.09
     Lager
    -0.09
     bol
    -0.09
    Tor
    -0.09
    POSITIVE LOGITS
     busy
    0.49
     Busy
    0.41
     busiest
    0.40
    busy
    0.37
    Busy
    0.37
     hectic
    0.32
     workload
    0.31
     BUS
    0.25
    _busy
    0.23
     overloaded
    0.23
    Activations Density 0.372%

    No Known Activations