© 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. 6760
    Prev
    Next
    INDEX
    Explanations

    ominous signs accumulating

    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
     physically
    -0.12
     phys
    -0.12
    alink
    -0.11
     downfall
    -0.10
     backbone
    -0.10
     Physical
    -0.10
     prolong
    -0.10
     bodily
    -0.10
     downstairs
    -0.10
    Physical
    -0.09
    POSITIVE LOGITS
     mortar
    0.11
     erected
    0.11
     shimmer
    0.11
     corro
    0.10
     fertil
    0.10
     duct
    0.10
     gust
    0.10
     tess
    0.10
     matrimon
    0.10
     glitter
    0.10
    Activations Density 0.360%

    No Known Activations