© 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. 50420
    Prev
    Next
    INDEX
    Explanations

    4-digit numbers and financial terms

    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
     applaud
    -0.13
     Bail
    -0.11
    Congratulations
    -0.10
     Congratulations
    -0.10
     amused
    -0.10
     applause
    -0.10
     laughing
    -0.10
    assis
    -0.10
     yup
    -0.09
     Accent
    -0.09
    POSITIVE LOGITS
     frightened
    0.11
     agon
    0.10
     Fee
    0.09
    yles
    0.09
    fee
    0.09
     effected
    0.09
     bankrupt
    0.09
     fee
    0.09
     stubborn
    0.09
     resignation
    0.09
    Activations Density 0.012%

    No Known Activations