© 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. 28923
    Prev
    Next
    INDEX
    Explanations

    doors and related

    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
     Downs
    -0.12
     Erica
    -0.10
    adder
    -0.10
     downs
    -0.10
    âĢİ
    -0.10
    jay
    -0.09
    aley
    -0.09
    ingu
    -0.09
    cons
    -0.09
     indiv
    -0.09
    POSITIVE LOGITS
     door
    0.28
     doors
    0.27
     Door
    0.21
     hinges
    0.20
     opens
    0.20
     opened
    0.19
     Doors
    0.19
    -door
    0.19
    door
    0.19
    Door
    0.18
    Activations Density 0.071%

    No Known Activations