© 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. 46593
    Prev
    Next
    INDEX
    Explanations

    Site 2, Router 2

    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
    alo
    -0.08
    bjerg
    -0.08
    iten
    -0.08
    ASF
    -0.07
    ifu
    -0.07
    tti
    -0.07
     Perr
    -0.07
    uge
    -0.07
     Baum
    -0.07
     pole
    -0.07
    POSITIVE LOGITS
     Ortiz
    0.13
     ?:
    0.12
     stad
    0.12
     lashes
    0.11
    (do
    0.10
     stag
    0.10
    rss
    0.10
    (ins
    0.10
     Pants
    0.10
    -next
    0.10
    Activations Density 0.060%

    No Known Activations