© 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. 7029
    Prev
    Next
    INDEX
    Explanations

    relational calculus and IgD Hispanic leukemia

    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
     ãĤ¢
    -0.21
    .ArrayList
    -0.20
    >alert
    -0.17
     ankles
    -0.17
     asteroids
    -0.17
     أ
    -0.17
    ãĤ¢
    -0.16
     Atkins
    -0.16
     atheists
    -0.16
     actionPerformed
    -0.16
    POSITIVE LOGITS
    .JSONException
    0.11
    .EventHandler
    0.09
    .LayoutStyle
    0.08
     newArr
    0.08
     wrist
    0.08
    prepend
    0.07
    .Shapes
    0.07
    .MouseEvent
    0.07
     perimeter
    0.07
    ESC
    0.07
    Activations Density 2.310%

    No Known Activations