© 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. 16504
    Prev
    Next
    INDEX
    Explanations

    gene expression programs

    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
     Bene
    -0.12
    /Base
    -0.10
     softened
    -0.10
     Trot
    -0.10
     slippery
    -0.09
     extern
    -0.09
     friction
    -0.09
     paddle
    -0.09
     soft
    -0.09
     palp
    -0.09
    POSITIVE LOGITS
     hun
    0.13
     heads
    0.11
     straight
    0.10
     lowering
    0.10
     downward
    0.10
     pri
    0.10
     lowered
    0.10
    straight
    0.10
     heading
    0.10
     incl
    0.10
    Activations Density 0.006%

    No Known Activations