© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 31913
    Prev
    Next
    INDEX
    Explanations

    a little

    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
     stark
    -0.10
     shorthand
    -0.10
     eventual
    -0.10
    POR
    -0.09
     rd
    -0.09
    eks
    -0.09
     Shen
    -0.09
     largely
    -0.09
    nett
    -0.09
     outnumber
    -0.09
    POSITIVE LOGITS
    depending
    0.12
     Enough
    0.10
     depending
    0.10
     enough
    0.10
    ZA
    0.10
    ivers
    0.09
     nostalg
    0.09
     (<
    0.09
     Peel
    0.09
    QL
    0.08
    Activations Density 0.085%

    No Known Activations