© 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. 16937
    Prev
    Next
    INDEX
    Explanations

    `contact`, `interaction`, `overlap`

    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
    _bel
    -0.10
     chair
    -0.10
     bel
    -0.10
     Kaplan
    -0.10
     DEV
    -0.10
     dred
    -0.10
     splitted
    -0.10
     sund
    -0.10
     rede
    -0.10
     Bel
    -0.09
    POSITIVE LOGITS
     mutual
    0.19
     contact
    0.18
     intertw
    0.17
     exchanging
    0.17
     overlapping
    0.17
     exchange
    0.16
     overlap
    0.16
     matching
    0.16
     clash
    0.16
     exchanged
    0.16
    Activations Density 0.064%

    No Known Activations