© 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. 49497
    Prev
    Next
    INDEX
    Explanations

    floor

    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
     ground
    -0.14
     underwater
    -0.13
     grounds
    -0.12
    ground
    -0.12
     roadside
    -0.10
     skin
    -0.10
    Skin
    -0.09
     terrestrial
    -0.09
     street
    -0.09
     downstream
    -0.09
    POSITIVE LOGITS
     Ceiling
    0.13
     rugs
    0.10
     beneath
    0.10
     ceiling
    0.10
     mats
    0.10
     Bene
    0.10
     Presenter
    0.10
     cabinets
    0.10
     furniture
    0.10
     Dich
    0.10
    Activations Density 0.086%

    No Known Activations