© 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. 91807
    Prev
    Next
    INDEX
    Explanations

    opportunities and audiences

    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
     sellers
    -0.11
     seller
    -0.09
    Seller
    -0.09
     sender
    -0.09
     service
    -0.08
    .codes
    -0.08
    pare
    -0.08
     charged
    -0.08
    vel
    -0.08
     resigned
    -0.08
    POSITIVE LOGITS
     audiences
    0.26
     audience
    0.23
     Audience
    0.19
     opportunities
    0.19
     Opportunities
    0.19
     viewers
    0.17
     demand
    0.15
     nich
    0.15
     opportunity
    0.15
     supportive
    0.15
    Activations Density 0.091%

    No Known Activations