© 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. 49143
    Prev
    Next
    INDEX
    Explanations

    exist/is/are/has

    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
    GM
    -0.09
    /cms
    -0.09
    nee
    -0.09
     GM
    -0.09
     Roland
    -0.09
     Raz
    -0.09
     keyed
    -0.09
     Hayden
    -0.08
    YE
    -0.08
    gn
    -0.08
    POSITIVE LOGITS
     inplace
    0.12
     exist
    0.12
    ovsky
    0.11
     exists
    0.10
     outnumber
    0.10
     oversh
    0.10
    ORE
    0.10
     Ult
    0.10
    .
    0.09
     existed
    0.09
    Activations Density 1.108%

    No Known Activations