© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 18494
    Prev
    Next
    INDEX
    Explanations

    surrounding or spatial descriptors

    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
    Negative Logits
     indign
    -0.10
     mint
    -0.10
     aux
    -0.10
     airborne
    -0.10
     bottoms
    -0.10
    alink
    -0.10
    EMENT
    -0.10
     ale
    -0.10
    Ø°
    -0.09
    Spec
    -0.09
    POSITIVE LOGITS
     surrounded
    0.14
     surrounding
    0.14
     Surround
    0.13
     surrounds
    0.12
     sometimes
    0.12
     Sometimes
    0.11
     tactile
    0.11
     texture
    0.11
     easiest
    0.10
     surround
    0.10
    Activations Density 0.049%

    No Known Activations