© 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. 90587
    Prev
    Next
    INDEX
    Explanations

    living and working

    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
     residential
    -0.32
     housing
    -0.30
     residence
    -0.29
     residences
    -0.29
     Residential
    -0.27
     Residence
    -0.24
     Housing
    -0.24
     dwelling
    -0.24
     homes
    -0.23
     resides
    -0.23
    POSITIVE LOGITS
     commute
    0.13
     Kash
    0.11
     Zak
    0.11
    _subplot
    0.10
     cooking
    0.10
     bef
    0.10
     commuting
    0.10
     Orch
    0.10
     utilities
    0.10
     Employment
    0.10
    Activations Density 0.459%

    No Known Activations