© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 87942
    Prev
    Next
    INDEX
    Explanations

    busy or busiest state

    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
     standby
    -0.11
    IJ
    -0.09
     bedtime
    -0.09
     pinch
    -0.08
    iminal
    -0.08
     freely
    -0.08
     whichever
    -0.08
    å¾ħ
    -0.08
    iro
    -0.08
     Bed
    -0.08
    POSITIVE LOGITS
     affairs
    0.15
     busiest
    0.14
     busy
    0.13
    busy
    0.13
    /bus
    0.12
     Busy
    0.12
    Busy
    0.12
    aison
    0.11
     tasks
    0.11
     elsewhere
    0.11
    Activations Density 0.043%

    No Known Activations