© 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. 30865
    Prev
    Next
    INDEX
    Explanations

    if-else constructs

    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
    orro
    -0.12
    utto
    -0.10
    loh
    -0.10
    igo
    -0.09
     Topics
    -0.09
     dev
    -0.09
    justice
    -0.09
    ="[
    -0.09
    ÙĦا
    -0.09
     Hue
    -0.09
    POSITIVE LOGITS
     caul
    0.10
     physique
    0.10
     pickup
    0.09
    pane
    0.08
    mere
    0.08
    Body
    0.08
     middle
    0.08
    stride
    0.08
     twig
    0.08
     Donovan
    0.08
    Activations Density 0.086%

    No Known Activations