© 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. 17052
    Prev
    Next
    INDEX
    Explanations

    Indian place names and personal names

    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
     Bangladesh
    -0.12
     Malaysian
    -0.12
     Malays
    -0.12
     Islamabad
    -0.11
     Fayette
    -0.11
     Malaysia
    -0.11
     Alexandria
    -0.10
     tear
    -0.10
     Lahore
    -0.10
     Sri
    -0.10
    POSITIVE LOGITS
     Maharashtra
    0.25
     Pune
    0.21
     Mumbai
    0.18
     Bombay
    0.15
    àª
    0.13
    à«
    0.13
     Chicago
    0.12
     Massachusetts
    0.12
    Chicago
    0.12
     MID
    0.12
    Activations Density 0.299%

    No Known Activations