© 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. 15237
    Prev
    Next
    INDEX
    Explanations

    why is that

    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
    oret
    -0.12
     birth
    -0.11
     Bes
    -0.10
    logen
    -0.10
     Bout
    -0.10
     Deutschland
    -0.10
     verdad
    -0.10
    nice
    -0.09
     cheat
    -0.09
    baum
    -0.09
    POSITIVE LOGITS
     called
    0.12
     important
    0.10
     Called
    0.10
     termed
    0.10
    called
    0.10
     that
    0.10
     että
    0.09
    cker
    0.09
     Important
    0.09
     whenever
    0.08
    Activations Density 0.020%

    No Known Activations