© 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. 50247
    Prev
    Next
    INDEX
    Explanations

    toys, gadgets, tools, games

    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
    rophy
    -0.09
    isp
    -0.09
     Laur
    -0.08
    appen
    -0.08
    scratch
    -0.08
    aking
    -0.08
     Donovan
    -0.08
     wr
    -0.08
    credible
    -0.07
     canned
    -0.07
    POSITIVE LOGITS
    /tools
    0.16
     toys
    0.15
    /devices
    0.13
     gadgets
    0.12
    /games
    0.12
     tools
    0.12
     Toys
    0.12
     devices
    0.11
    aab
    0.11
    ingly
    0.11
    Activations Density 0.008%

    No Known Activations