© 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. 6710
    Prev
    Next
    INDEX
    Explanations

    jointly sharing

    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
     imbalance
    -0.09
     manten
    -0.09
     unrest
    -0.09
    Pk
    -0.09
     restraining
    -0.08
     knocking
    -0.08
    mvc
    -0.08
     undo
    -0.08
    announcement
    -0.08
    864
    -0.08
    POSITIVE LOGITS
     shared
    0.58
     Shared
    0.48
    shared
    0.46
    Shared
    0.42
    -shared
    0.42
     jointly
    0.41
     sharing
    0.40
    åħ±
    0.38
    /shared
    0.35
    -sharing
    0.35
    Activations Density 0.177%

    No Known Activations