© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 30563
    Prev
    Next
    INDEX
    Explanations

    names ending in unn, Chinese provinces

    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
    æį®
    -0.11
    pedia
    -0.10
    ette
    -0.10
    ÑĤÑĥ
    -0.10
     tug
    -0.09
     muted
    -0.09
     relief
    -0.09
    esta
    -0.09
    otti
    -0.09
     flare
    -0.09
    POSITIVE LOGITS
    ally
    0.11
    ALLY
    0.10
    ery
    0.10
    eken
    0.10
    aign
    0.10
    vos
    0.09
    ily
    0.09
    ihan
    0.09
    ernel
    0.09
     nem
    0.09
    Activations Density 0.008%

    No Known Activations