© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 15858
    Prev
    Next
    INDEX
    Explanations

    looks like, like to

    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
    lain
    -0.11
    {/*
    -0.10
     lief
    -0.10
     realizing
    -0.10
     Laurie
    -0.10
    newsletter
    -0.10
     alike
    -0.10
    ripper
    -0.10
    bee
    -0.10
    otron
    -0.09
    POSITIVE LOGITS
    idle
    0.10
    /how
    0.10
     compared
    0.10
     firsthand
    0.09
    sans
    0.09
     proced
    0.08
     circum
    0.08
     underneath
    0.08
     inside
    0.08
    opez
    0.08
    Activations Density 0.009%

    No Known Activations