© 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. 5150
    Prev
    Next
    INDEX
    Explanations

    met neighbor or guest

    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
    uron
    -0.09
    ế
    -0.09
     attract
    -0.08
     celib
    -0.08
     Stra
    -0.08
     anticipation
    -0.07
     Garn
    -0.07
     replic
    -0.07
     amph
    -0.07
     accrued
    -0.07
    POSITIVE LOGITS
     babys
    0.20
     neighbor
    0.17
     neighbors
    0.16
     guest
    0.15
     neighb
    0.15
     neighbour
    0.15
     neighbours
    0.15
     assisted
    0.15
     borrowed
    0.14
     tutoring
    0.14
    Activations Density 0.216%

    No Known Activations