© 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. 88581
    Prev
    Next
    INDEX
    Explanations

    profitable business and industry

    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
     shoppers
    -0.13
     shopper
    -0.12
    -shopping
    -0.11
    nis
    -0.10
     shopping
    -0.10
     hail
    -0.10
    andy
    -0.09
     bipolar
    -0.09
     ident
    -0.09
    ez
    -0.09
    POSITIVE LOGITS
     profitable
    0.20
     lucrative
    0.20
     profits
    0.19
     profit
    0.19
    profits
    0.17
     brisk
    0.16
    profit
    0.15
     profitability
    0.14
     cottage
    0.14
     billions
    0.14
    Activations Density 0.057%

    No Known Activations