© 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. 31917
    Prev
    Next
    INDEX
    Explanations

    developer tools and forums

    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
    ers
    -0.09
    res
    -0.08
    toa
    -0.08
    elen
    -0.07
    (er
    -0.07
     APPRO
    -0.07
     Barnes
    -0.07
    å°ij
    -0.07
     bang
    -0.07
    gs
    -0.07
    POSITIVE LOGITS
    hood
    0.16
     freshness
    0.11
     Ashe
    0.11
     fores
    0.11
    chine
    0.11
     cleanly
    0.11
     conven
    0.10
     jus
    0.10
     defining
    0.10
     innocence
    0.10
    Activations Density 0.006%

    No Known Activations