© 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. 50162
    Prev
    Next
    INDEX
    Explanations

    remote, rural, isolated areas

    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
     Inside
    -0.10
     inside
    -0.10
     systematically
    -0.10
     SHORT
    -0.10
    abad
    -0.09
     Laz
    -0.09
    Inside
    -0.09
     downstairs
    -0.09
    cope
    -0.09
    DK
    -0.08
    POSITIVE LOGITS
     remot
    0.27
     remote
    0.26
     isolated
    0.25
     isolation
    0.22
     secluded
    0.22
     rural
    0.20
     nowhere
    0.20
     Remote
    0.20
     isolate
    0.20
    remote
    0.19
    Activations Density 0.147%

    No Known Activations