© 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. 32548
    Prev
    Next
    INDEX
    Explanations

    .com, .org

    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
    zion
    -0.09
     hive
    -0.08
    ajes
    -0.08
    ixer
    -0.07
    nten
    -0.07
    Api
    -0.07
     thr
    -0.07
    ù
    -0.07
    BUR
    -0.07
    tic
    -0.07
    POSITIVE LOGITS
    alli
    0.10
     Duch
    0.10
     Percy
    0.10
     cata
    0.10
    pei
    0.10
     prez
    0.10
     Hus
    0.10
     Rossi
    0.10
    <?,
    0.09
    Mu
    0.09
    Activations Density 0.003%

    No Known Activations