© 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. 5394
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units or punctuation

    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
    wal
    -0.09
    printStats
    -0.09
    adesh
    -0.08
     asses
    -0.08
     nu
    -0.08
     Libraries
    -0.07
     Ness
    -0.07
     Orch
    -0.07
    wid
    -0.07
     valu
    -0.07
    POSITIVE LOGITS
    auer
    0.13
    âĦ¢
    0.12
     stump
    0.10
    nite
    0.10
    s
    0.10
     damned
    0.10
     ama
    0.10
    ãĢģ“
    0.10
     rein
    0.10
     sede
    0.10
    Activations Density 0.002%

    No Known Activations