© 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. 31188
    Prev
    Next
    INDEX
    Explanations

    numbers and separators

    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
     nightly
    -0.12
     Leading
    -0.10
     clock
    -0.10
     Ãłs
    -0.10
     Laf
    -0.10
    throat
    -0.09
    mgr
    -0.09
    urr
    -0.09
    leading
    -0.09
     seconds
    -0.09
    POSITIVE LOGITS
    otos
    0.09
     Trident
    0.09
     Hanson
    0.09
     mata
    0.09
     Tud
    0.08
     Trent
    0.08
     tud
    0.08
    ÃŃs
    0.08
     restr
    0.08
     beneficiary
    0.08
    Activations Density 0.021%

    No Known Activations