© 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. 17036
    Prev
    Next
    INDEX
    Explanations

    verbs ending in -ed, -ing, -ive, -ishes, -ages, -ating

    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
    odal
    -0.11
     emotionally
    -0.10
    /all
    -0.10
     ill
    -0.10
     remotely
    -0.09
    æ²»
    -0.09
     holidays
    -0.09
     Elo
    -0.09
    oder
    -0.09
    eat
    -0.09
    POSITIVE LOGITS
     loft
    0.11
    edBy
    0.10
    eton
    0.10
    itionally
    0.09
    uze
    0.09
     Gio
    0.09
    (ed
    0.09
    pit
    0.09
    lessly
    0.08
    agne
    0.08
    Activations Density 0.030%

    No Known Activations