© 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. 30140
    Prev
    Next
    INDEX
    Explanations

    popular or newest

    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
    eel
    -0.10
    idy
    -0.09
    -double
    -0.09
     Harding
    -0.08
     asymmetric
    -0.08
     Dund
    -0.08
    stakes
    -0.08
    ndl
    -0.08
    agraph
    -0.08
    ogne
    -0.08
    POSITIVE LOGITS
     Popular
    0.14
     newest
    0.13
     oldest
    0.13
     popular
    0.13
     unpopular
    0.12
     upt
    0.12
     favorites
    0.12
     extremes
    0.12
    popular
    0.12
    Popular
    0.11
    Activations Density 0.060%

    No Known Activations