© 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. 5135
    Prev
    Next
    INDEX
    Explanations

    advertise business and services

    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
     Dana
    -0.10
    das
    -0.09
    defer
    -0.09
     refr
    -0.09
    lis
    -0.08
     noss
    -0.08
     OPTION
    -0.08
     Purch
    -0.08
     fountain
    -0.08
     conversations
    -0.08
    POSITIVE LOGITS
     upcoming
    0.17
     availability
    0.16
     services
    0.16
     forthcoming
    0.15
     advertise
    0.14
    services
    0.14
     offerings
    0.14
     advert
    0.13
    Services
    0.13
     Services
    0.13
    Activations Density 0.076%

    No Known Activations