© 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. 16882
    Prev
    Next
    INDEX
    Explanations

    segregated accounts, trusted vendors, Intuit, Tata, Joint Commission

    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
     Pou
    -0.09
     DIY
    -0.09
     bib
    -0.08
     Lod
    -0.08
    slaught
    -0.08
    OE
    -0.08
     Bols
    -0.08
     homemade
    -0.08
     boyc
    -0.08
     illeg
    -0.08
    POSITIVE LOGITS
     undergo
    0.11
    ateg
    0.11
     actu
    0.10
     Audit
    0.10
     penetration
    0.10
    elu
    0.10
    PILE
    0.10
     Bra
    0.10
     audits
    0.10
     Cer
    0.09
    Activations Density 0.006%

    No Known Activations