© 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. 32804
    Prev
    Next
    INDEX
    Explanations

    System; using

    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
    isi
    -0.10
     Lap
    -0.10
    elay
    -0.09
     Pey
    -0.09
     sac
    -0.09
    ritz
    -0.09
     unchecked
    -0.09
     Syndrome
    -0.09
    ixon
    -0.09
    ello
    -0.09
    POSITIVE LOGITS
     esc
    0.10
     presum
    0.09
     satisfied
    0.09
     Qu
    0.09
     tid
    0.09
     satisf
    0.09
     repl
    0.08
    pas
    0.08
     rec
    0.08
    aton
    0.08
    Activations Density 0.004%

    No Known Activations