© 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. 91266
    Prev
    Next
    INDEX
    Explanations

    equi

    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
    arding
    -0.08
    aming
    -0.07
     written
    -0.07
    otland
    -0.07
    EEP
    -0.07
    ec
    -0.07
    imu
    -0.07
    azer
    -0.07
     work
    -0.07
     Styles
    -0.07
    POSITIVE LOGITS
    ALLY
    0.13
    ifax
    0.13
    ally
    0.11
    ilibrium
    0.11
    enne
    0.11
    ations
    0.11
     alo
    0.11
     equ
    0.11
    ickt
    0.11
    uhe
    0.11
    Activations Density 0.003%

    No Known Activations