© 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. 15742
    Prev
    Next
    INDEX
    Explanations

    variations of "write"

    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
    went
    -0.10
     Sommer
    -0.09
    ogh
    -0.09
    amas
    -0.09
     Reflection
    -0.08
    ponent
    -0.08
    recall
    -0.08
    rescia
    -0.08
    .bd
    -0.08
     ext
    -0.08
    POSITIVE LOGITS
     writ
    0.12
     prescriptions
    0.10
    (write
    0.10
    -write
    0.10
    _Write
    0.10
     write
    0.10
     writeln
    0.10
     rewritten
    0.10
     Write
    0.10
     illeg
    0.10
    Activations Density 0.085%

    No Known Activations