© 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. 46382
    Prev
    Next
    INDEX
    Explanations

    Meng, peng, Schn, eng

    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
     Auch
    -0.08
     reel
    -0.08
     rever
    -0.08
    etry
    -0.08
    ETS
    -0.08
    fos
    -0.08
     frustration
    -0.08
    otal
    -0.08
     stal
    -0.07
    view
    -0.07
    POSITIVE LOGITS
    o
    0.11
    ster
    0.11
    lings
    0.11
    ubo
    0.11
     overnight
    0.10
    sters
    0.10
    nia
    0.10
    /native
    0.10
     Overnight
    0.10
    rams
    0.10
    Activations Density 0.004%

    No Known Activations