© 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. 115250
    Prev
    Next
    INDEX
    Explanations

    time 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
    oad
    -0.13
     иÑģп
    -0.11
     Patt
    -0.11
    afi
    -0.11
    decay
    -0.10
    añ
    -0.10
    redo
    -0.10
    ohon
    -0.10
     protagon
    -0.10
    leo
    -0.10
    POSITIVE LOGITS
     times
    0.25
     time
    0.23
     timings
    0.22
     date
    0.20
     timing
    0.19
    time
    0.17
     timeframe
    0.17
    æŶéĹ´
    0.16
     dates
    0.16
     вÑĢемÑı
    0.16
    Activations Density 0.148%

    No Known Activations