© 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. 15095
    Prev
    Next
    INDEX
    Explanations

    companies, shipping

    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
     Hiring
    -0.11
     whitelist
    -0.10
     hires
    -0.10
    áo
    -0.10
     exter
    -0.10
     Nim
    -0.10
    hire
    -0.10
    utar
    -0.09
     empir
    -0.09
    enaire
    -0.09
    POSITIVE LOGITS
     Cla
    0.10
    OID
    0.09
    burgh
    0.09
    ntag
    0.08
     Hag
    0.08
     cac
    0.08
     equally
    0.08
     Mars
    0.08
    cents
    0.08
    agg
    0.07
    Activations Density 0.040%

    No Known Activations