© 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. 31659
    Prev
    Next
    INDEX
    Explanations

    Arabic names and places

    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
    دÙĩ
    -0.11
     sovere
    -0.08
    cobra
    -0.08
     la
    -0.08
     alter
    -0.07
     pool
    -0.07
     tried
    -0.07
    ÙĦÙī
    -0.06
     Slam
    -0.06
     trope
    -0.06
    POSITIVE LOGITS
    azeera
    0.11
    querque
    0.11
    Ùij
    0.11
    adians
    0.11
    gende
    0.11
    avian
    0.11
     Kah
    0.11
     proudly
    0.11
    awah
    0.10
    adian
    0.10
    Activations Density 0.038%

    No Known Activations