© 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. 27225
    Prev
    Next
    INDEX
    Explanations

    Chinese names and East Asian characters

    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
    antar
    -0.10
    upy
    -0.09
    nst
    -0.09
    sic
    -0.09
     Dy
    -0.09
    ä¾Ľ
    -0.09
    divide
    -0.09
    eded
    -0.09
    elas
    -0.08
     oui
    -0.08
    POSITIVE LOGITS
    bert
    0.10
     Sent
    0.09
    _mu
    0.09
    's
    0.09
    uada
    0.08
     bic
    0.08
     esk
    0.08
     Yale
    0.08
    -y
    0.08
    ichen
    0.08
    Activations Density 0.013%

    No Known Activations