© 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. 17042
    Prev
    Next
    INDEX
    Explanations

    optical communication and related fields

    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
     scare
    -0.09
    ESS
    -0.09
     least
    -0.09
     scattered
    -0.09
    allo
    -0.09
    icl
    -0.09
    least
    -0.09
     preced
    -0.09
    esson
    -0.09
    endi
    -0.09
    POSITIVE LOGITS
    estr
    0.10
    ismet
    0.10
    der
    0.10
    acam
    0.09
     shel
    0.09
    PJ
    0.09
     Cav
    0.09
    rede
    0.08
    ists
    0.08
     incidence
    0.08
    Activations Density 0.033%

    No Known Activations