© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48373
    Prev
    Next
    INDEX
    Explanations

    room numbers or floors

    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
    jeta
    -0.12
    Ord
    -0.10
     fountain
    -0.09
     ponds
    -0.09
    tract
    -0.08
    umu
    -0.08
     roadside
    -0.08
     Spi
    -0.08
     topping
    -0.08
     subst
    -0.08
    POSITIVE LOGITS
     rooms
    0.24
     Rooms
    0.23
     Room
    0.23
     room
    0.22
    Room
    0.21
    ROOM
    0.20
     Floor
    0.19
    Rooms
    0.19
    rooms
    0.19
    Floor
    0.19
    Activations Density 1.063%

    No Known Activations