© 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. 7919
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units or patent identifiers

    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
     ide
    -0.10
     Poe
    -0.09
     QT
    -0.09
    Toggle
    -0.09
     Mans
    -0.08
     foc
    -0.08
    _lt
    -0.08
     Ital
    -0.08
     busted
    -0.08
     mans
    -0.08
    POSITIVE LOGITS
    WSC
    0.10
    ACL
    0.10
    itten
    0.10
    DBC
    0.10
    sing
    0.09
     slash
    0.09
     dislikes
    0.09
     Cli
    0.09
     consecutive
    0.09
     copies
    0.09
    Activations Density 0.001%

    No Known Activations