© 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. 16908
    Prev
    Next
    INDEX
    Explanations

    next day or subsequent time

    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
     reduced
    -0.09
    ild
    -0.09
     thick
    -0.09
    Unnamed
    -0.09
    CE
    -0.09
    Century
    -0.09
     Others
    -0.09
    kt
    -0.09
     horizontally
    -0.09
     maxim
    -0.09
    POSITIVE LOGITS
     morning
    0.20
     day
    0.18
     night
    0.17
     evening
    0.17
     afternoon
    0.16
     Morning
    0.12
     week
    0.11
     Evening
    0.10
     moment
    0.10
    woke
    0.10
    Activations Density 0.044%

    No Known Activations