© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 90272
    Prev
    Next
    INDEX
    Explanations

    play games or make decisions

    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
     involves
    -0.08
    -hover
    -0.08
     sw
    -0.08
     glowing
    -0.08
    viron
    -0.08
     rever
    -0.08
     Gaw
    -0.08
     workings
    -0.07
     akin
    -0.07
     commun
    -0.07
    POSITIVE LOGITS
     Editorial
    0.12
     route
    0.11
     road
    0.11
     path
    0.11
    bm
    0.11
    /reg
    0.10
    replacement
    0.10
    bff
    0.10
     games
    0.10
     subscribed
    0.10
    Activations Density 0.003%

    No Known Activations