© 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. 6728
    Prev
    Next
    INDEX
    Explanations

    roy royalty Royce

    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
    wear
    -0.10
    plat
    -0.09
    akis
    -0.09
    rei
    -0.09
    rsa
    -0.09
    ophile
    -0.09
     crim
    -0.09
    Gov
    -0.09
    OOM
    -0.09
     coz
    -0.09
    POSITIVE LOGITS
    alty
    0.14
     Mustang
    0.10
     arp
    0.09
     @{
    0.09
     prer
    0.09
    _fps
    0.09
    tea
    0.08
    -bearing
    0.08
     Lah
    0.08
    uela
    0.08
    Activations Density 0.047%

    No Known Activations