© 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. 5256
    Prev
    Next
    INDEX
    Explanations

    groups and locations

    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
    unte
    -0.09
     Hod
    -0.09
    ye
    -0.08
    ossier
    -0.08
    î
    -0.08
    AIM
    -0.08
    ..↵
    -0.08
    oto
    -0.08
    ucci
    -0.08
     Buddy
    -0.08
    POSITIVE LOGITS
    HEMA
    0.11
    !”
    0.09
    ”—
    0.09
     Beau
    0.09
    )—
    0.09
    acen
    0.09
    ),"
    0.09
     Blow
    0.09
    chaft
    0.09
     distracting
    0.08
    Activations Density 0.003%

    No Known Activations