© 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. 49619
    Prev
    Next
    INDEX
    Explanations

    work or effort

    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
    adt
    -0.10
     sung
    -0.10
    odel
    -0.10
     Freder
    -0.10
    å¾ħ
    -0.10
     linger
    -0.10
     Controlled
    -0.09
     sui
    -0.09
    linger
    -0.09
     dwell
    -0.09
    POSITIVE LOGITS
     involved
    0.15
     effort
    0.15
    -intensive
    0.15
     expended
    0.14
    /time
    0.14
     exert
    0.13
     required
    0.13
     upkeep
    0.11
     intensive
    0.11
    required
    0.10
    Activations Density 0.085%

    No Known Activations