© 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. 48822
    Prev
    Next
    INDEX
    Explanations

    unless required, except in

    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
    .gdx
    -0.09
    usa
    -0.08
    leton
    -0.08
     Watt
    -0.08
     Gregg
    -0.08
     bitcoin
    -0.08
     NB
    -0.08
     Sy
    -0.08
     Spin
    -0.08
     vex
    -0.07
    POSITIVE LOGITS
     Klo
    0.12
     Cla
    0.11
    -chat
    0.11
     confer
    0.10
     Platforms
    0.10
     Nep
    0.10
    ات
    0.10
    Downloader
    0.10
     Lama
    0.10
     Zar
    0.10
    Activations Density 0.177%

    No Known Activations