© 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. 5568
    Prev
    Next
    INDEX
    Explanations

    adjective endings like -y or -ly

    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
     Bliss
    -0.12
     bliss
    -0.11
    azen
    -0.10
     madness
    -0.10
    s
    -0.10
     rage
    -0.10
     configur
    -0.09
     daunting
    -0.09
    enci
    -0.09
    uze
    -0.09
    POSITIVE LOGITS
     little
    0.13
    iest
    0.11
    -up
    0.10
    iness
    0.10
     darn
    0.09
     tricks
    0.09
    -ass
    0.09
     lad
    0.09
     tunes
    0.09
     tricky
    0.09
    Activations Density 0.034%

    No Known Activations