© 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. 32078
    Prev
    Next
    INDEX
    Explanations

    domain suffixes

    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
     Tray
    -0.09
     Tamb
    -0.08
     en
    -0.07
    prs
    -0.07
     Mej
    -0.07
     Hay
    -0.07
    ampa
    -0.07
     exposure
    -0.07
     Hornets
    -0.07
    âĢİ
    -0.07
    POSITIVE LOGITS
    .ua
    0.13
    ,www
    0.12
    egg
    0.12
    pell
    0.11
    ijn
    0.11
    empor
    0.11
     nu
    0.11
    uyo
    0.11
     volum
    0.11
    sumer
    0.10
    Activations Density 0.066%

    No Known Activations