© 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. 29206
    Prev
    Next
    INDEX
    Explanations

    home and office locations

    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
    locals
    -0.11
     lay
    -0.10
    aris
    -0.10
     statically
    -0.10
    iese
    -0.10
    gor
    -0.10
    localized
    -0.10
    jan
    -0.10
     amateurs
    -0.10
    iros
    -0.10
    POSITIVE LOGITS
     downtown
    0.22
     workplace
    0.19
     school
    0.18
     abroad
    0.18
     hospital
    0.18
     elsewhere
    0.16
     Downtown
    0.16
     public
    0.16
     neighbors
    0.16
     church
    0.15
    Activations Density 0.358%

    No Known Activations