© 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. 15078
    Prev
    Next
    INDEX
    Explanations

    pier and pierina

    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
    URE
    -0.11
    upe
    -0.10
    erner
    -0.10
     anomal
    -0.10
    ateurs
    -0.10
    lich
    -0.10
    FU
    -0.10
    hausen
    -0.10
     spawned
    -0.10
    bao
    -0.10
    POSITIVE LOGITS
    cing
    0.11
    ogi
    0.11
    ced
    0.11
     Paolo
    0.08
    uggy
    0.08
    ucci
    0.08
    ech
    0.08
    EntryPoint
    0.08
    acc
    0.08
    cer
    0.07
    Activations Density 0.003%

    No Known Activations