© 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. 17313
    Prev
    Next
    INDEX
    Explanations

    door related words

    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
    IBE
    -0.10
     Kunst
    -0.09
    ikan
    -0.08
    anel
    -0.08
    AGO
    -0.08
     bodily
    -0.08
     Mö
    -0.08
    Äij
    -0.08
     branding
    -0.08
     leap
    -0.08
    POSITIVE LOGITS
     door
    0.26
     doors
    0.22
     Door
    0.18
    Door
    0.16
    door
    0.16
     Doors
    0.15
     gates
    0.14
    éŨ
    0.14
     gate
    0.13
    -door
    0.13
    Activations Density 0.006%

    No Known Activations