© 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. 114003
    Prev
    Next
    INDEX
    Explanations

    Korean Peninsula and related topics

    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
     Baton
    -0.09
     Colorado
    -0.09
    argon
    -0.09
    eline
    -0.09
     rough
    -0.09
     maur
    -0.08
     deb
    -0.08
    irma
    -0.08
     Firm
    -0.08
     recourse
    -0.08
    POSITIVE LOGITS
     DPR
    0.14
     Peninsula
    0.13
     peninsula
    0.12
     Koreans
    0.11
    bean
    0.10
    ball
    0.10
     Korean
    0.10
     Seoul
    0.10
     Yong
    0.10
     Kore
    0.09
    Activations Density 0.015%

    No Known Activations