© 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. 15436
    Prev
    Next
    INDEX
    Explanations

    wallet

    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
     helmets
    -0.14
     helmet
    -0.11
    agher
    -0.11
     Helmet
    -0.10
    rug
    -0.10
     Tit
    -0.10
    _bed
    -0.10
    YE
    -0.10
     rooft
    -0.10
     org
    -0.10
    POSITIVE LOGITS
     Raid
    0.09
     pants
    0.09
     ordinary
    0.09
     Medi
    0.09
     normal
    0.09
     regular
    0.09
     mainstream
    0.08
     thankfully
    0.08
     Shir
    0.08
     execut
    0.08
    Activations Density 0.039%

    No Known Activations