© 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. 115292
    Prev
    Next
    INDEX
    Explanations

    home financing and purchase

    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
     hotels
    -0.13
     billionaire
    -0.12
     Hotels
    -0.12
     Hotel
    -0.11
     hotel
    -0.10
     reboot
    -0.10
     zap
    -0.10
     alias
    -0.10
    zap
    -0.10
    otel
    -0.10
    POSITIVE LOGITS
     mortgage
    0.24
     Mortgage
    0.20
     homeowners
    0.18
     homeowner
    0.17
     mort
    0.17
    mort
    0.17
     refin
    0.16
     mortgages
    0.16
    -mort
    0.15
     amort
    0.15
    Activations Density 0.278%

    No Known Activations