© 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. 92245
    Prev
    Next
    INDEX
    Explanations

    long durations of time spent

    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
     until
    -0.15
     Until
    -0.15
    Years
    -0.14
    Until
    -0.14
     years
    -0.14
    assi
    -0.13
     till
    -0.13
    years
    -0.12
     someday
    -0.12
     Years
    -0.12
    POSITIVE LOGITS
     since
    0.13
     already
    0.12
     consecutive
    0.11
     Hours
    0.11
     hour
    0.11
     consec
    0.11
     hours
    0.10
     hasn
    0.10
     now
    0.10
     HOUR
    0.10
    Activations Density 0.214%

    No Known Activations