© 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. 116681
    Prev
    Next
    INDEX
    Explanations

    closing and sealing

    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
     loosen
    -0.14
     loos
    -0.12
     lighten
    -0.12
    -striped
    -0.11
     wav
    -0.11
    decoded
    -0.11
     disag
    -0.11
     freely
    -0.11
    Stride
    -0.11
     diluted
    -0.11
    POSITIVE LOGITS
     sealing
    0.36
     locking
    0.34
     shutting
    0.32
     closure
    0.32
     closing
    0.30
     closures
    0.29
     Closure
    0.29
    locking
    0.28
     Closing
    0.28
     closed
    0.27
    Activations Density 0.346%

    No Known Activations