© 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. 5418
    Prev
    Next
    INDEX
    Explanations

    Marie, PaCa, Yueting, ARMSTRONG, Miacora

    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
     situ
    -0.08
     Kel
    -0.08
    é©
    -0.07
    /Sub
    -0.07
     MSG
    -0.07
     Intermediate
    -0.07
     jack
    -0.07
     bum
    -0.07
     Wallet
    -0.07
     ridden
    -0.06
    POSITIVE LOGITS
    ccd
    0.12
     culpa
    0.11
    oice
    0.10
    (android
    0.10
     Skyl
    0.10
    (Int
    0.10
     superf
    0.10
    Prefab
    0.09
     fileList
    0.09
    apolis
    0.09
    Activations Density 0.009%

    No Known Activations