© 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. 31847
    Prev
    Next
    INDEX
    Explanations

    rooms in houses

    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
     extracted
    -0.11
    aura
    -0.10
    Republican
    -0.10
     hurt
    -0.09
    asant
    -0.09
    andan
    -0.09
     carrot
    -0.09
     insider
    -0.09
    /by
    -0.09
     copied
    -0.09
    POSITIVE LOGITS
     bathrooms
    0.24
     bedrooms
    0.20
     bathroom
    0.19
     kitchen
    0.17
     toilets
    0.17
     kitchens
    0.16
     rooms
    0.15
     classrooms
    0.15
     Bathroom
    0.15
     offices
    0.15
    Activations Density 0.170%

    No Known Activations