© 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. 27647
    Prev
    Next
    INDEX
    Explanations

    an article followed by a noun

    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
     util
    -0.20
     Whilst
    -0.17
    Whilst
    -0.15
     whilst
    -0.14
     lia
    -0.14
     recogn
    -0.14
     eg
    -0.11
     fav
    -0.11
     utilise
    -0.11
     emphas
    -0.11
    POSITIVE LOGITS
     onward
    0.18
     volte
    0.16
     snag
    0.16
     likes
    0.16
     advert
    0.16
     worrying
    0.14
     dod
    0.14
     dove
    0.13
    tat
    0.12
     contrib
    0.12
    Activations Density 0.854%

    No Known Activations