© 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. 5857
    Prev
    Next
    INDEX
    Explanations

    file extensions (.rs, .txt, .cpp)

    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
    &#
    -0.09
     Murphy
    -0.08
     bubbles
    -0.08
     sensible
    -0.08
     hj
    -0.08
     dia
    -0.08
     servicing
    -0.08
     horm
    -0.08
     Hern
    -0.08
    sov
    -0.08
    POSITIVE LOGITS
     <<↵
    0.12
     shadow
    0.10
     wholesale
    0.10
     discharge
    0.10
     (~
    0.10
    >>↵
    0.09
     </>↵
    0.09
    >>)
    0.09
     [["
    0.09
     [[
    0.09
    Activations Density 0.855%

    No Known Activations