© 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. 48585
    Prev
    Next
    INDEX
    Explanations

    first thing

    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
    /help
    -0.10
    pong
    -0.10
    /ca
    -0.09
     Rice
    -0.08
     relay
    -0.08
     consecutive
    -0.08
    /ag
    -0.08
    Alchemy
    -0.08
     propel
    -0.08
     Cain
    -0.08
    POSITIVE LOGITS
     First
    0.13
     first
    0.13
     FIRST
    0.12
     tomorrow
    0.12
    -first
    0.12
    first
    0.11
    _first
    0.11
    First
    0.11
     last
    0.11
     mañana
    0.11
    Activations Density 0.020%

    No Known Activations