© 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. 47938
    Prev
    Next
    INDEX
    Explanations

    knight

    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
    ystery
    -0.12
     hypert
    -0.12
    ulk
    -0.11
    Hints
    -0.10
    ikki
    -0.10
    oki
    -0.10
     Clarkson
    -0.10
     Hutchinson
    -0.10
     heroic
    -0.10
     fore
    -0.10
    POSITIVE LOGITS
     Templ
    0.11
    err
    0.10
     templ
    0.09
     dames
    0.09
    mare
    0.09
     Malta
    0.09
     Err
    0.08
    mares
    0.08
     err
    0.08
     shining
    0.08
    Activations Density 0.051%

    No Known Activations