© 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. 50246
    Prev
    Next
    INDEX
    Explanations

    artists and institutions

    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
    (TM
    -0.10
     coun
    -0.09
     Cannabis
    -0.09
     VIP
    -0.09
     analyst
    -0.09
     overlays
    -0.09
     canv
    -0.09
    vip
    -0.08
     Corinthians
    -0.08
     Cann
    -0.08
    POSITIVE LOGITS
     curator
    0.16
     inaug
    0.15
     programme
    0.15
     Programme
    0.15
     conven
    0.15
     resid
    0.15
     Incontri
    0.15
     curated
    0.15
     Sonic
    0.15
     interdisciplinary
    0.15
    Activations Density 2.352%

    No Known Activations