© 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. 7006
    Prev
    Next
    INDEX
    Explanations

    version 2 licenses

    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
    &nbsp
    -0.15
    ||(
    -0.15
    <strong
    -0.13
    &&(
    -0.13
    *
    -0.13
    "
    -0.13
    ”çļĦ
    -0.12
    (
    -0.12
    printStats
    -0.12
    '↵↵↵↵
    -0.12
    POSITIVE LOGITS
    ØĮ
    0.14
    –
    0.13
     –
    0.12
    /'
    0.12
    ://
    0.12
    ‘
    0.12
    ï¼ļ
    0.12
     -
    0.11
    /*
    0.11
     —
    0.11
    Activations Density 1.025%

    No Known Activations