© 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. 116833
    Prev
    Next
    INDEX
    Explanations

    variety of / degree of

    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
     suce
    -0.11
     ...↵↵↵↵
    -0.10
     bé
    -0.09
     inval
    -0.09
    _signature
    -0.09
    Tween
    -0.09
    ResourceManager
    -0.09
    Č↵
    -0.09
     ness
    -0.09
    avec
    -0.09
    POSITIVE LOGITS
    vang
    0.09
     olan
    0.08
    apat
    0.08
    aar
    0.08
     oracle
    0.08
     para
    0.08
    fel
    0.07
     cuanto
    0.07
    294
    0.07
     harga
    0.07
    Activations Density 0.134%

    No Known Activations