© 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. 116428
    Prev
    Next
    INDEX
    Explanations

    script editor

    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
    <|fim_middle|>
    -0.13
    <|endoftext|>
    -0.11
    Slash
    -0.10
    ,.↵↵
    -0.09
    uard
    -0.09
    orf
    -0.08
     {{
    -0.08
    Photon
    -0.08
    ért
    -0.08
    tog
    -0.08
    POSITIVE LOGITS
     reportedly
    0.10
    <section
    0.10
     cul
    0.10
     Smithsonian
    0.10
    (click
    0.09
     precis
    0.09
     Zimmer
    0.09
     tit
    0.09
    eworld
    0.09
     Modal
    0.09
    Activations Density 0.016%

    No Known Activations