© 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. 26477
    Prev
    Next
    INDEX
    Explanations

    announced or revealed

    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
     normalization
    -0.09
     Stark
    -0.09
     dk
    -0.09
     freshly
    -0.08
     blames
    -0.08
    ashi
    -0.08
     blamed
    -0.08
     Moral
    -0.08
    iste
    -0.08
     rec
    -0.08
    POSITIVE LOGITS
     mystery
    0.29
     secrecy
    0.28
     mysterious
    0.28
     secretive
    0.26
     teased
    0.25
     clues
    0.25
     tease
    0.24
     crypt
    0.24
     teasing
    0.24
     Mystery
    0.24
    Activations Density 0.187%

    No Known Activations