© 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. 17702
    Prev
    Next
    INDEX
    Explanations

    neighborhoods and districts

    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
     horizontal
    -0.10
     onstage
    -0.09
     openings
    -0.09
    tee
    -0.09
    enne
    -0.09
     Horizontal
    -0.09
     Huckabee
    -0.09
     Pane
    -0.09
     Oman
    -0.09
     UK
    -0.09
    POSITIVE LOGITS
     neighborhoods
    0.49
     neighborhood
    0.47
     neighbourhood
    0.43
     Neighborhood
    0.35
    neighbor
    0.30
     suburb
    0.28
     district
    0.27
     suburbs
    0.27
     districts
    0.26
     area
    0.25
    Activations Density 0.560%

    No Known Activations