© 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. 116457
    Prev
    Next
    INDEX
    Explanations

    geographic locations and centers

    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
     Bij
    -0.08
     GK
    -0.07
     (++
    -0.07
     Reconstruction
    -0.07
     ore
    -0.07
     secret
    -0.07
     tod
    -0.07
     Ordered
    -0.07
     Fors
    -0.07
    ื
    -0.07
    POSITIVE LOGITS
     unofficial
    0.15
     mundial
    0.12
     Alo
    0.11
    tabs
    0.11
     America
    0.11
    -bold
    0.11
     vit
    0.11
     Wer
    0.11
    Wer
    0.11
    /media
    0.10
    Activations Density 0.269%

    No Known Activations