© 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. 17590
    Prev
    Next
    INDEX
    Explanations

    quote or estimate

    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
     commissions
    -0.11
    lest
    -0.10
    imity
    -0.10
    urer
    -0.10
    /org
    -0.10
     Contributor
    -0.10
     rewarding
    -0.09
     Paid
    -0.09
     Pay
    -0.09
     Kop
    -0.09
    POSITIVE LOGITS
     estimate
    0.31
     quote
    0.31
     estimates
    0.30
     quotation
    0.29
     quotes
    0.29
     quotations
    0.28
     quoted
    0.27
     Estimates
    0.27
     Quote
    0.26
     Estimate
    0.26
    Activations Density 0.508%

    No Known Activations