© 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. 4400
    Prev
    Next
    INDEX
    Explanations

    brand visibility and promotion

    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
     comforts
    -0.10
    Compression
    -0.09
     satisfying
    -0.09
     Swe
    -0.08
    ((-
    -0.08
    accepted
    -0.08
    Feel
    -0.08
     comforting
    -0.08
     nobody
    -0.08
     greeted
    -0.08
    POSITIVE LOGITS
     exposure
    0.36
     publicity
    0.32
     Exposure
    0.32
     visibility
    0.30
     boost
    0.25
     Visibility
    0.25
     boosts
    0.24
     exposures
    0.23
    Visibility
    0.23
     Boost
    0.22
    Activations Density 0.336%

    No Known Activations