© 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. 114429
    Prev
    Next
    INDEX
    Explanations

    pant, panc, punct, pneum prefixes

    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
    rij
    -0.09
     Clothes
    -0.09
     Lilly
    -0.08
     lap
    -0.08
     clothes
    -0.08
     fleece
    -0.08
     cloth
    -0.07
     cloves
    -0.07
     ostensibly
    -0.07
     Clothing
    -0.07
    POSITIVE LOGITS
    ewan
    0.13
     shortages
    0.12
    antz
    0.12
    exchange
    0.12
    -span
    0.11
     Swal
    0.11
     Linden
    0.11
     spanning
    0.10
    ctr
    0.10
    aker
    0.10
    Activations Density 0.001%

    No Known Activations