© 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. 89327
    Prev
    Next
    INDEX
    Explanations

    Saudi Arabia, Somalia, azole, pipe

    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
    -,
    -0.19
     -,
    -0.15
    -/
    -0.13
    ,[
    -0.13
    IFI
    -0.12
    ;\
    -0.12
     âĶľâĶĢâĶĢ
    -0.12
     furthermore
    -0.12
    #,
    -0.12
    &amp
    -0.12
    POSITIVE LOGITS
     anda
    0.07
     stal
    0.07
     ans
    0.06
     amd
    0.06
    lez
    0.06
    ï¼ĸ
    0.05
     ad
    0.05
    ittle
    0.05
     sic
    0.05
     safeg
    0.05
    Activations Density 0.697%

    No Known Activations