© 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. 30327
    Prev
    Next
    INDEX
    Explanations

    Latin word endings

    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
     swollen
    -0.09
     personalised
    -0.09
     duly
    -0.08
     apo
    -0.08
     hj
    -0.08
     swell
    -0.08
     specialised
    -0.08
     sede
    -0.07
     thanks
    -0.07
     pou
    -0.07
    POSITIVE LOGITS
     Dix
    0.13
     harus
    0.12
     honest
    0.11
     ellas
    0.11
    unger
    0.11
    contres
    0.11
     ("
    0.11
     dile
    0.10
     sane
    0.10
     Vanity
    0.10
    Activations Density 0.358%

    No Known Activations