© 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. 31536
    Prev
    Next
    INDEX
    Explanations

    following

    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
     ones
    -0.12
    /common
    -0.10
     basics
    -0.09
     Ones
    -0.09
     fundamentals
    -0.08
    ewn
    -0.08
     STATUS
    -0.08
     counterparts
    -0.08
     status
    -0.08
    epar
    -0.08
    POSITIVE LOGITS
     contains
    0.10
    unday
    0.10
    ulin
    0.10
     stamped
    0.09
    sted
    0.09
    oto
    0.09
     Unified
    0.09
     confession
    0.09
     presenta
    0.09
    OTO
    0.09
    Activations Density 0.027%

    No Known Activations