© 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. 113164
    Prev
    Next
    INDEX
    Explanations

    currency and exchange

    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
    icity
    -0.08
     ske
    -0.07
    iris
    -0.07
    rog
    -0.07
     McGr
    -0.07
    istan
    -0.07
     intrinsic
    -0.07
     RNG
    -0.07
    eries
    -0.07
    zilla
    -0.07
    POSITIVE LOGITS
     exchange
    0.13
    converter
    0.12
    vet
    0.12
     Exchange
    0.12
    uma
    0.11
    efe
    0.11
     denomin
    0.10
     hypoth
    0.10
    rier
    0.10
     Dank
    0.10
    Activations Density 0.016%

    No Known Activations