© 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. 32487
    Prev
    Next
    INDEX
    Explanations

    foreign, outside, abroad

    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
     Als
    -0.10
     fod
    -0.10
    ogan
    -0.10
     oss
    -0.10
     Bernard
    -0.09
    crypt
    -0.09
     highs
    -0.09
     Fs
    -0.09
    aru
    -0.09
    oco
    -0.08
    POSITIVE LOGITS
     outside
    0.12
     Outside
    0.10
    outside
    0.10
    streams
    0.09
    Outside
    0.09
     customs
    0.09
    å¤ĸ
    0.09
     external
    0.09
     outer
    0.09
     abroad
    0.08
    Activations Density 0.034%

    No Known Activations