© 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. 26259
    Prev
    Next
    INDEX
    Explanations

    marketing and advertising campaigns

    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
     reim
    -0.13
    Commercial
    -0.10
     proposing
    -0.10
     prof
    -0.10
    emer
    -0.09
     debounce
    -0.09
     imposing
    -0.09
     deliber
    -0.09
     rearr
    -0.09
     commercial
    -0.09
    POSITIVE LOGITS
     promotion
    0.25
     marketing
    0.24
     outreach
    0.23
     campaigns
    0.22
     Promotion
    0.21
     promotional
    0.21
     publicity
    0.21
     Marketing
    0.20
     Outreach
    0.20
     advertising
    0.19
    Activations Density 0.532%

    No Known Activations