© 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. 112879
    Prev
    Next
    INDEX
    Explanations

    financial contributions and payments

    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
     smugg
    -0.10
     outdoors
    -0.10
     locally
    -0.10
     Dipl
    -0.09
     merc
    -0.09
     interviewing
    -0.09
     jardin
    -0.09
     treat
    -0.09
     indoor
    -0.09
     mixing
    -0.09
    POSITIVE LOGITS
     donating
    0.15
     donations
    0.15
     payments
    0.14
     payer
    0.14
     financial
    0.14
     Donate
    0.14
     finance
    0.14
     compuls
    0.14
     donation
    0.14
     Pay
    0.14
    Activations Density 0.006%

    No Known Activations