© 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. 7606
    Prev
    Next
    INDEX
    Explanations

    and/or prepositional phrases

    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
     dew
    -0.10
     Heather
    -0.10
     SGD
    -0.10
     prosecute
    -0.10
    iode
    -0.09
    aniu
    -0.09
     Nico
    -0.09
    iah
    -0.09
    bate
    -0.09
    acier
    -0.09
    POSITIVE LOGITS
     sides
    0.11
     bottom
    0.10
    itel
    0.09
     side
    0.09
    iger
    0.08
     topLeft
    0.08
    -and
    0.08
    çĿ
    0.08
     Coun
    0.08
     Aub
    0.08
    Activations Density 0.066%

    No Known Activations