© 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. 113743
    Prev
    Next
    INDEX
    Explanations

    foreign or exotic origin

    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
     autob
    -0.10
     goof
    -0.08
     raz
    -0.08
     Bran
    -0.08
     stor
    -0.08
     uber
    -0.08
    236
    -0.07
    ugin
    -0.07
     Dud
    -0.07
     Lanc
    -0.07
    POSITIVE LOGITS
     exotic
    0.24
     alien
    0.14
     xen
    0.12
     tropical
    0.12
     Alien
    0.12
     Foreign
    0.12
    .Native
    0.11
     Ex
    0.11
     jungle
    0.11
    _EX
    0.11
    Activations Density 0.076%

    No Known Activations