© 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. 112490
    Prev
    Next
    INDEX
    Explanations

    a summary

    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
    sing
    -0.10
    loo
    -0.09
     Bench
    -0.08
    325
    -0.08
     Singh
    -0.08
    ora
    -0.08
     inevitable
    -0.08
     fetish
    -0.08
    legate
    -0.08
     benchmarks
    -0.08
    POSITIVE LOGITS
     list
    0.29
     overview
    0.27
     summary
    0.25
     rundown
    0.24
     breakdown
    0.24
     recap
    0.20
     outline
    0.19
     synopsis
    0.19
     description
    0.18
     glimpse
    0.18
    Activations Density 0.404%

    No Known Activations