© 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. 30531
    Prev
    Next
    INDEX
    Explanations

    easy followed by a word

    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
    ingly
    -0.10
     solid
    -0.08
    nable
    -0.08
    contest
    -0.08
    heart
    -0.08
    Modules
    -0.08
     fault
    -0.08
    MOVED
    -0.08
     Plains
    -0.08
    -archive
    -0.08
    POSITIVE LOGITS
    EDA
    0.10
     EZ
    0.10
    eda
    0.10
    isky
    0.10
     Bake
    0.10
     chair
    0.10
    /AP
    0.10
     Patron
    0.10
     Way
    0.10
     detach
    0.10
    Activations Density 0.031%

    No Known Activations