© 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. 4875
    Prev
    Next
    INDEX
    Explanations

    ads and commercials

    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
     misunder
    -0.12
    Posting
    -0.11
     cata
    -0.10
     cuff
    -0.09
    allah
    -0.09
    owell
    -0.09
     Newtown
    -0.09
     fatt
    -0.09
    bian
    -0.09
     nal
    -0.09
    POSITIVE LOGITS
     ads
    0.28
     Ads
    0.24
     advertisements
    0.23
     adverts
    0.22
     annoying
    0.21
     interruptions
    0.21
     interrupt
    0.20
    Ads
    0.20
     sponsored
    0.20
     intrusive
    0.19
    Activations Density 0.054%

    No Known Activations