© 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. 14288
    Prev
    Next
    INDEX
    Explanations

    currency and values

    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
     prof
    -0.08
     purchase
    -0.08
     resp
    -0.08
    BlockSize
    -0.07
     conc
    -0.07
     employed
    -0.07
     rec
    -0.07
     liquid
    -0.07
    :)
    -0.07
    allet
    -0.07
    POSITIVE LOGITS
     upwards
    0.13
    Asc
    0.12
     Asc
    0.12
    cha
    0.11
     nightly
    0.11
    _daily
    0.11
    iga
    0.10
     implic
    0.10
    /day
    0.10
     culp
    0.10
    Activations Density 0.025%

    No Known Activations