© 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. 91252
    Prev
    Next
    INDEX
    Explanations

    once

    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
    igo
    -0.10
    chein
    -0.09
    wich
    -0.09
    ilia
    -0.09
    ento
    -0.09
    oda
    -0.08
    itable
    -0.08
    {/*
    -0.08
    annie
    -0.08
    igi
    -0.08
    POSITIVE LOGITS
     once
    0.91
    once
    0.75
     Once
    0.71
    Once
    0.67
    _once
    0.46
    .once
    0.39
    .Once
    0.37
     einmal
    0.31
    _ONCE
    0.27
    onces
    0.25
    Activations Density 0.386%

    No Known Activations