© 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. 31969
    Prev
    Next
    INDEX
    Explanations

    public hospitals

    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
     Taiwan
    -0.13
     Filip
    -0.12
     Taiwanese
    -0.12
     Taipei
    -0.12
     Manila
    -0.12
    åı°
    -0.11
     Singapore
    -0.11
     Malay
    -0.11
    Singapore
    -0.10
     Philippines
    -0.10
    POSITIVE LOGITS
     Garr
    0.10
    azine
    0.10
    âĦ
    0.09
    Egypt
    0.09
     Pik
    0.09
     unsub
    0.09
     matched
    0.09
     medically
    0.09
     Nebraska
    0.08
     Plains
    0.08
    Activations Density 0.033%

    No Known Activations