© 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. 116016
    Prev
    Next
    INDEX
    Explanations

    simulation and game software

    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
    adero
    -0.10
     Bingo
    -0.09
     Orr
    -0.09
    fax
    -0.09
     dee
    -0.09
     Gap
    -0.08
     Alt
    -0.08
     Fritz
    -0.08
     tart
    -0.08
     chew
    -0.08
    POSITIVE LOGITS
     download
    0.13
     simulator
    0.13
     apk
    0.12
    ulator
    0.12
     app
    0.12
     android
    0.12
     Simulator
    0.12
     free
    0.12
     Android
    0.12
     software
    0.12
    Activations Density 0.025%

    No Known Activations