© 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. 89687
    Prev
    Next
    INDEX
    Explanations

    mutual/joint actions or relationships

    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
     we
    -0.09
    iska
    -0.09
    inth
    -0.08
    we
    -0.08
    uch
    -0.08
    ava
    -0.08
    car
    -0.07
    undi
    -0.07
    aco
    -0.07
    alia
    -0.07
    POSITIVE LOGITS
     together
    0.47
     mutually
    0.45
     jointly
    0.40
     mutual
    0.40
     Together
    0.39
    Together
    0.38
     collectively
    0.33
     Mutual
    0.30
    gether
    0.29
     beide
    0.27
    Activations Density 0.069%

    No Known Activations