© 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. 6413
    Prev
    Next
    INDEX
    Explanations

    time constraints, wasting, trials, lapse, consuming, saving

    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
    -0.07
    олÑĮ
    -0.07
     Dul
    -0.07
    seg
    -0.07
    uff
    -0.07
    iac
    -0.06
     Hampton
    -0.06
    aza
    -0.06
    inder
    -0.06
    annel
    -0.06
    POSITIVE LOGITS
     spent
    0.19
    -consuming
    0.17
     consuming
    0.16
    -saving
    0.16
    ,time
    0.16
    -tested
    0.16
    .timeScale
    0.15
    pieces
    0.15
    /time
    0.15
    spent
    0.15
    Activations Density 0.072%

    No Known Activations