© 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. 25654
    Prev
    Next
    INDEX
    Explanations

    if statements and conjunctions

    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
    577
    -0.10
     coloc
    -0.09
    (ws
    -0.09
    chy
    -0.09
     Morrison
    -0.09
    arias
    -0.08
    ouch
    -0.08
     cush
    -0.08
     Gunn
    -0.08
     Cox
    -0.08
    POSITIVE LOGITS
     similarly
    0.24
     likewise
    0.23
     Similarly
    0.20
     Likewise
    0.20
     Dit
    0.19
    Similarly
    0.19
     vice
    0.17
    Lik
    0.16
     Conversely
    0.16
     convers
    0.15
    Activations Density 0.216%

    No Known Activations