© 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. 16718
    Prev
    Next
    INDEX
    Explanations

    update and summary information

    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
     pseud
    -0.11
     Twe
    -0.10
     spontaneously
    -0.10
     Yelp
    -0.10
    aksi
    -0.09
     Glover
    -0.09
    allet
    -0.09
     pulver
    -0.09
    ipel
    -0.09
    empre
    -0.08
    POSITIVE LOGITS
     recap
    0.32
     briefed
    0.29
     briefing
    0.27
     Recap
    0.24
     updates
    0.24
     update
    0.23
     summarize
    0.23
     summary
    0.22
     Updates
    0.22
     summaries
    0.21
    Activations Density 0.168%

    No Known Activations