© 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. 49986
    Prev
    Next
    INDEX
    Explanations

    links or file paths

    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
     Duffy
    -0.09
    undle
    -0.09
     Ide
    -0.09
     Domino
    -0.08
    Bookmark
    -0.08
    iculos
    -0.08
    ERC
    -0.08
    /documents
    -0.08
     duro
    -0.08
    ills
    -0.08
    POSITIVE LOGITS
     acompanh
    0.11
     Weston
    0.10
     Wis
    0.10
     beforehand
    0.10
     accordingly
    0.10
     exp
    0.09
     tw
    0.09
     execut
    0.09
     Kent
    0.09
     Lists
    0.09
    Activations Density 0.001%

    No Known Activations