© 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. 16980
    Prev
    Next
    INDEX
    Explanations

    matching sunglasses, black, neck

    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
    cko
    -0.08
    ourg
    -0.08
     winters
    -0.08
    oya
    -0.08
     cores
    -0.07
     å±
    -0.07
     liken
    -0.07
    iero
    -0.07
     layers
    -0.07
     machines
    -0.07
    POSITIVE LOGITS
     matching
    0.12
    Bookmark
    0.12
     matched
    0.12
     neatly
    0.11
    -black
    0.11
     similarly
    0.11
     sentiments
    0.11
    egis
    0.11
     bookmark
    0.11
    -cli
    0.10
    Activations Density 0.029%

    No Known Activations