© 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. 114750
    Prev
    Next
    INDEX
    Explanations

    which/that followed by noun

    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
     whereby
    -0.11
    aze
    -0.10
     eminent
    -0.08
     appar
    -0.08
    eni
    -0.08
     obviously
    -0.08
    avana
    -0.08
    oor
    -0.08
    hton
    -0.08
    rif
    -0.08
    POSITIVE LOGITS
     cater
    0.15
    ’ll
    0.13
     seamlessly
    0.13
     promise
    0.12
     promises
    0.12
     Await
    0.12
     capture
    0.12
     oo
    0.12
     redefine
    0.12
     will
    0.11
    Activations Density 0.141%

    No Known Activations