© 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. 14713
    Prev
    Next
    INDEX
    Explanations

    upstairs locations

    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
     Chase
    -0.10
     Tab
    -0.09
     bottom
    -0.09
     tab
    -0.08
     Bing
    -0.08
    Americ
    -0.08
     revers
    -0.07
     Lara
    -0.07
     Bach
    -0.07
     overload
    -0.07
    POSITIVE LOGITS
     attic
    0.15
    /down
    0.14
     north
    0.13
     loft
    0.13
     northern
    0.12
    north
    0.12
     rooftop
    0.12
     upstairs
    0.11
     northeast
    0.11
     Loft
    0.11
    Activations Density 0.032%

    No Known Activations