© 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. 16989
    Prev
    Next
    INDEX
    Explanations

    mathematical assignments or computations

    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
    oth
    -0.09
     (^
    -0.09
    anja
    -0.09
    itm
    -0.08
    :>
    -0.08
    IFn
    -0.08
     Ast
    -0.08
    /Dk
    -0.08
    charm
    -0.08
    PJ
    -0.08
    POSITIVE LOGITS
    <|endoftext|>
    0.12
     caul
    0.09
    /url
    0.09
     sensational
    0.08
    inters
    0.08
    mainwindow
    0.08
    successfully
    0.08
     bay
    0.08
     gener
    0.08
     combinations
    0.08
    Activations Density 0.012%

    No Known Activations