© 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. 28483
    Prev
    Next
    INDEX
    Explanations

    before, during, or after

    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
    rang
    -0.10
    aes
    -0.10
    afa
    -0.10
    gua
    -0.10
    deen
    -0.10
     Reached
    -0.10
    ikal
    -0.10
    neas
    -0.10
    unday
    -0.10
     Dirt
    -0.10
    POSITIVE LOGITS
    vel
    0.09
    ada
    0.08
     Lub
    0.08
     immediately
    0.08
     Hud
    0.08
     vamp
    0.08
     simultaneously
    0.07
    amar
    0.07
     SAC
    0.07
     meanwhile
    0.07
    Activations Density 0.045%

    No Known Activations