© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 25731
    Prev
    Next
    INDEX
    Explanations

    monetary values or amounts

    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
     styl
    -0.11
    _rates
    -0.11
     earned
    -0.11
     Wick
    -0.11
     charged
    -0.11
     Ky
    -0.11
    (seconds
    -0.11
     hourly
    -0.10
     earns
    -0.10
     hour
    -0.10
    POSITIVE LOGITS
     millions
    0.31
     million
    0.26
     Millions
    0.24
     Million
    0.22
     MILL
    0.21
     thousands
    0.18
     multim
    0.18
    million
    0.17
    -million
    0.17
     lump
    0.16
    Activations Density 0.255%

    No Known Activations