© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 6082
    Prev
    Next
    INDEX
    Explanations

    It's patterns related to 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
     exp
    -0.10
     refr
    -0.09
     flatt
    -0.08
    ervoir
    -0.08
     decline
    -0.08
    lds
    -0.08
     deco
    -0.08
    oods
    -0.08
     filles
    -0.08
     gu
    -0.08
    POSITIVE LOGITS
     afternoon
    0.13
     day
    0.13
     morning
    0.13
     originated
    0.12
    ching
    0.11
     evening
    0.11
     DAY
    0.11
     Monday
    0.11
     Wednesday
    0.11
     Begins
    0.11
    Activations Density 0.020%

    No Known Activations