© 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. 7623
    Prev
    Next
    INDEX
    Explanations

    Rex/RX followed by specific words

    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
    -cond
    -0.10
    erry
    -0.10
    ateurs
    -0.09
    ancing
    -0.09
     Alicia
    -0.09
    ument
    -0.09
     unm
    -0.08
    SSION
    -0.08
    ÃŃa
    -0.08
    asca
    -0.08
    POSITIVE LOGITS
    ulti
    0.14
     Tillerson
    0.12
    cellent
    0.11
    roat
    0.10
     Trucks
    0.09
    es
    0.09
    leigh
    0.09
    azy
    0.09
     prow
    0.09
    áŁĴáŀ
    0.09
    Activations Density 0.019%

    No Known Activations