© 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. 16579
    Prev
    Next
    INDEX
    Explanations

    spatial relationships

    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
    orden
    -0.12
    bia
    -0.12
     backstage
    -0.12
     Inside
    -0.12
    ffc
    -0.11
    _inside
    -0.11
     Meadows
    -0.11
    Inside
    -0.11
    ÑĮ
    -0.11
    osa
    -0.10
    POSITIVE LOGITS
     nearby
    0.29
     beside
    0.29
     opposite
    0.24
     adjacent
    0.22
     next
    0.21
     neighbouring
    0.20
     ahead
    0.19
     neighboring
    0.18
     Nearby
    0.18
     surrounding
    0.17
    Activations Density 0.111%

    No Known Activations