© 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. 5560
    Prev
    Next
    INDEX
    Explanations

    near or nearby 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
     Furn
    -0.10
     Pavilion
    -0.09
     consort
    -0.09
     Rhodes
    -0.09
     conditioned
    -0.09
    legg
    -0.09
     Fail
    -0.09
     Haupt
    -0.09
     Solomon
    -0.09
     Cor
    -0.08
    POSITIVE LOGITS
     nearby
    0.42
     near
    0.40
     nearest
    0.39
    near
    0.35
     Near
    0.35
     Nearby
    0.32
    Near
    0.32
    _near
    0.30
    nearest
    0.30
     nearer
    0.27
    Activations Density 0.106%

    No Known Activations