© 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. 48279
    Prev
    Next
    INDEX
    Explanations

    time of day and dates

    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
     Sinn
    -0.10
     invol
    -0.10
     ;)
    -0.09
     Thorn
    -0.09
     everytime
    -0.09
    /articles
    -0.09
     segregation
    -0.09
     Jenner
    -0.09
    irected
    -0.09
    enia
    -0.09
    POSITIVE LOGITS
     now
    0.12
     verg
    0.11
     already
    0.11
     daytime
    0.10
     outside
    0.09
    acle
    0.09
     satur
    0.09
    now
    0.08
     schon
    0.08
     maintenant
    0.08
    Activations Density 0.022%

    No Known Activations