© 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. 31982
    Prev
    Next
    INDEX
    Explanations

    spoiled or spoilers

    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
    Fake
    -0.09
     pep
    -0.08
    wap
    -0.08
    eer
    -0.08
    ej
    -0.08
    Inv
    -0.08
    mas
    -0.08
     Angelo
    -0.08
    073
    -0.08
     Typed
    -0.08
    POSITIVE LOGITS
     rotten
    0.18
     spo
    0.16
     spoiled
    0.14
     Spo
    0.14
     spoil
    0.13
    -rich
    0.13
    spo
    0.12
    Spo
    0.12
     riches
    0.11
     rich
    0.11
    Activations Density 0.003%

    No Known Activations