© 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. 17498
    Prev
    Next
    INDEX
    Explanations

    Scandinavian languages

    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
     dozens
    -0.12
     bli
    -0.11
     Aside
    -0.11
     också
    -0.11
    èģ
    -0.11
     beginnings
    -0.10
    usual
    -0.10
     skl
    -0.10
    ‘s
    -0.10
     Perr
    -0.10
    POSITIVE LOGITS
    :s
    0.24
     Norwegian
    0.23
     kå
    0.22
     och
    0.22
     Swedish
    0.21
     Danish
    0.19
     og
    0.18
     ”
    0.18
     søker
    0.18
    ø
    0.17
    Activations Density 1.959%

    No Known Activations