© 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. 7596
    Prev
    Next
    INDEX
    Explanations

    page title

    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
     fro
    -0.11
    zelf
    -0.10
     Dodd
    -0.10
     Gauss
    -0.10
     //~
    -0.10
    chg
    -0.09
     Karma
    -0.09
    vice
    -0.09
    稿
    -0.09
     Alma
    -0.09
    POSITIVE LOGITS
     vou
    0.10
     Raphael
    0.09
     schwer
    0.08
    BTN
    0.08
     vir
    0.08
    avig
    0.08
     navigating
    0.08
     separate
    0.07
     Navigate
    0.07
    isplay
    0.07
    Activations Density 0.002%

    No Known Activations