© 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. 4558
    Prev
    Next
    INDEX
    Explanations

    ground or floor surfaces

    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
    /Admin
    -0.09
    ETHER
    -0.09
    rick
    -0.09
     Ingram
    -0.09
     Cann
    -0.09
    icorn
    -0.09
     entrev
    -0.09
    ensi
    -0.09
     embr
    -0.08
     Aer
    -0.08
    POSITIVE LOGITS
     floor
    0.36
     ground
    0.30
     Floor
    0.30
    floor
    0.27
     floors
    0.27
     flooring
    0.27
    -floor
    0.25
    Floor
    0.25
    (floor
    0.24
    _floor
    0.23
    Activations Density 0.225%

    No Known Activations