© 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. 7384
    Prev
    Next
    INDEX
    Explanations

    garage door

    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
     hotel
    -0.14
     broth
    -0.13
     Hotel
    -0.12
     Hotels
    -0.12
    hotel
    -0.12
     slur
    -0.11
     hotels
    -0.11
     hostel
    -0.11
    otel
    -0.11
     Harlem
    -0.10
    POSITIVE LOGITS
     garage
    0.30
     Garage
    0.29
     gar
    0.18
     GAR
    0.18
    Gar
    0.16
    gar
    0.14
     homeowner
    0.14
     basement
    0.13
     car
    0.13
     Gar
    0.12
    Activations Density 0.080%

    No Known Activations