© 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. 16458
    Prev
    Next
    INDEX
    Explanations

    start

    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
    anton
    -0.11
     dov
    -0.11
     ul
    -0.10
    cant
    -0.10
     litter
    -0.10
    amel
    -0.10
    177
    -0.10
     Tee
    -0.10
    Fi
    -0.10
    apers
    -0.09
    POSITIVE LOGITS
     engines
    0.18
     engine
    0.17
     machinery
    0.14
     machines
    0.13
     Engines
    0.11
     Engine
    0.11
     motors
    0.10
     up
    0.10
     generator
    0.10
     timers
    0.10
    Activations Density 0.314%

    No Known Activations