© 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. 31209
    Prev
    Next
    INDEX
    Explanations

    costs, expenses, contributions, reimbursements

    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
     confidentiality
    -0.11
     Nec
    -0.10
     longing
    -0.10
     cel
    -0.10
     captcha
    -0.10
     Fond
    -0.10
     sleeper
    -0.10
    peak
    -0.10
    Peak
    -0.10
     Bass
    -0.10
    POSITIVE LOGITS
     reimb
    0.20
     reimburse
    0.18
     contributions
    0.18
     contribution
    0.17
     costs
    0.17
     expenses
    0.17
     burden
    0.17
     cost
    0.17
     Contribution
    0.16
     generosity
    0.16
    Activations Density 0.028%

    No Known Activations