© 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. 49238
    Prev
    Next
    INDEX
    Explanations

    cash, cheque, dividends, account

    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
     overshadow
    -0.11
    argas
    -0.09
    -progress
    -0.09
     disfr
    -0.09
    &action
    -0.09
    (Equal
    -0.09
    shade
    -0.09
    Pes
    -0.09
     Jenkins
    -0.09
    rett
    -0.09
    POSITIVE LOGITS
     Cash
    0.17
     cash
    0.15
    Cash
    0.15
    cash
    0.11
    mere
    0.10
    _cash
    0.09
     cashier
    0.09
     liquidity
    0.09
     lightning
    0.08
     dividends
    0.08
    Activations Density 0.028%

    No Known Activations