© 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. 26873
    Prev
    Next
    INDEX
    Explanations

    files and code snippets

    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
     tough
    -0.09
    rome
    -0.08
     frankly
    -0.08
     premise
    -0.08
    iew
    -0.07
    sed
    -0.07
     exercised
    -0.07
     scrap
    -0.07
     parallels
    -0.07
     Sche
    -0.07
    POSITIVE LOGITS
    tracts
    0.10
    à¹Į
    0.10
     unst
    0.09
     filmer
    0.09
    hil
    0.09
     dint
    0.09
     trad
    0.09
    embros
    0.09
    unos
    0.09
     Barrel
    0.09
    Activations Density 1.808%

    No Known Activations