© 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. 46793
    Prev
    Next
    INDEX
    Explanations

    closing or shutting doors/lids

    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
     disposition
    -0.12
    idon
    -0.10
     cavalry
    -0.09
    Invariant
    -0.09
    olan
    -0.09
     dav
    -0.09
    addy
    -0.08
     consent
    -0.08
    ein
    -0.08
    /dist
    -0.08
    POSITIVE LOGITS
     behind
    0.17
     shut
    0.17
     gently
    0.12
     forcefully
    0.12
     Shut
    0.11
     frustrated
    0.11
    iga
    0.11
     shuts
    0.10
     reb
    0.10
     gentle
    0.10
    Activations Density 0.008%

    No Known Activations