© 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. 15970
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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
     Favor
    -0.10
     crit
    -0.09
     Kol
    -0.09
     biscuits
    -0.09
    TXT
    -0.09
     Listings
    -0.09
     txt
    -0.09
    iid
    -0.09
    åķĨ
    -0.09
     irreversible
    -0.09
    POSITIVE LOGITS
    -long
    0.11
     overhaul
    0.10
     Hin
    0.10
     circumference
    0.09
     cumulative
    0.09
     overwhel
    0.09
     total
    0.09
     branch
    0.09
    adal
    0.09
     cascade
    0.09
    Activations Density 0.310%

    No Known Activations