© 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. 7312
    Prev
    Next
    INDEX
    Explanations

    reciprocal or mutual relations

    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
    apo
    -0.10
     distr
    -0.09
     fas
    -0.08
     Whale
    -0.08
     whispers
    -0.08
     bump
    -0.08
    angep
    -0.08
     fon
    -0.08
     grouping
    -0.08
     overl
    -0.07
    POSITIVE LOGITS
     recipro
    0.50
     reciprocal
    0.49
     mutual
    0.41
     asym
    0.41
     balanced
    0.41
     recip
    0.39
     asymmetric
    0.38
     Mutual
    0.37
     imbalance
    0.37
     symmetric
    0.36
    Activations Density 0.417%

    No Known Activations