© 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. 48270
    Prev
    Next
    INDEX
    Explanations

    now, today, yet

    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
     Recent
    -0.13
     upcoming
    -0.13
    angan
    -0.12
     recent
    -0.12
     increasingly
    -0.11
    ï¿
    -0.10
    Recent
    -0.09
    ,on
    -0.09
     Soon
    -0.09
    JE
    -0.09
    POSITIVE LOGITS
     now
    0.24
     presently
    0.17
     noe
    0.16
     today
    0.16
     right
    0.15
     yet
    0.14
     NOW
    0.14
     ATM
    0.13
     toda
    0.13
     currently
    0.13
    Activations Density 0.756%

    No Known Activations