© 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. 117026
    Prev
    Next
    INDEX
    Explanations

    words and what follows

    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
     interchange
    -0.11
     nailed
    -0.09
    hot
    -0.08
     hot
    -0.08
    /mail
    -0.08
    /m
    -0.08
    :m
    -0.08
     acquaint
    -0.08
    back
    -0.08
     menus
    -0.08
    POSITIVE LOGITS
     youngest
    0.10
     Clarence
    0.10
     Clayton
    0.10
     Chandler
    0.10
    348
    0.10
     Lol
    0.10
     âĸĪâĸĪ
    0.10
    YO
    0.10
     tendencies
    0.10
     Khan
    0.09
    Activations Density 0.013%

    No Known Activations