© 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. 14961
    Prev
    Next
    INDEX
    Explanations

    names and places starting with ed

    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
     occasion
    -0.09
     possibility
    -0.09
    aley
    -0.09
     Opport
    -0.08
     opportunity
    -0.08
     con
    -0.08
    achs
    -0.08
    occasion
    -0.08
    ele
    -0.08
    enha
    -0.08
    POSITIVE LOGITS
    iele
    0.10
    kea
    0.10
     Perf
    0.10
    /original
    0.09
     ADV
    0.09
    Navigator
    0.09
    /Page
    0.09
     Wilde
    0.09
     cual
    0.09
    icer
    0.09
    Activations Density 0.002%

    No Known Activations