© 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. 116097
    Prev
    Next
    INDEX
    Explanations

    Mumbai and India cities

    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
    nown
    -0.09
     Nile
    -0.09
    ifu
    -0.09
    Nit
    -0.08
     Sheep
    -0.08
    |array
    -0.08
     (!((
    -0.08
    -pill
    -0.08
     cot
    -0.08
    cot
    -0.08
    POSITIVE LOGITS
    es
    0.14
     Maharashtra
    0.11
     Mumbai
    0.10
    aset
    0.10
     interstate
    0.10
    a
    0.09
    orro
    0.09
    ographic
    0.09
     Interstate
    0.09
    ingen
    0.09
    Activations Density 0.028%

    No Known Activations