© 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. 28430
    Prev
    Next
    INDEX
    Explanations

    frequency per unit 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
    yon
    -0.13
    olon
    -0.10
    aldi
    -0.10
    ongan
    -0.10
     tease
    -0.10
    iones
    -0.09
     Util
    -0.09
    ela
    -0.09
     ag
    -0.09
    strate
    -0.09
    POSITIVE LOGITS
     month
    0.19
     week
    0.18
     year
    0.18
     day
    0.17
     annum
    0.14
    day
    0.12
    /year
    0.12
    week
    0.12
    month
    0.12
     Month
    0.12
    Activations Density 0.086%

    No Known Activations