© 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. 14810
    Prev
    Next
    INDEX
    Explanations

    is/are followed by verb/determiner

    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
     Henderson
    -0.10
    RB
    -0.08
    unas
    -0.08
    /O
    -0.08
    ONO
    -0.08
    onis
    -0.08
    chine
    -0.08
    uner
    -0.08
    uso
    -0.08
     Transit
    -0.08
    POSITIVE LOGITS
    lest
    0.10
    omorphic
    0.10
     nag
    0.10
    lam
    0.10
    nt
    0.10
    ography
    0.10
     Hag
    0.09
     Whats
    0.09
    dg
    0.09
    veled
    0.09
    Activations Density 0.083%

    No Known Activations