© 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. 49523
    Prev
    Next
    INDEX
    Explanations

    surfaces and movement on them

    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
     yo
    -0.11
     dese
    -0.09
    soon
    -0.09
     wides
    -0.09
     seat
    -0.09
     biome
    -0.09
     Derm
    -0.09
     footprint
    -0.09
    smith
    -0.08
     pir
    -0.08
    POSITIVE LOGITS
     rebel
    0.12
     pavement
    0.11
     stairs
    0.11
     concrete
    0.11
     paths
    0.11
     floors
    0.11
     silent
    0.11
     subdued
    0.10
     road
    0.10
     worn
    0.10
    Activations Density 0.007%

    No Known Activations