© 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. 32354
    Prev
    Next
    INDEX
    Explanations

    big cats like lions and tigers

    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
     hitch
    -0.13
     elves
    -0.12
    otten
    -0.12
     troll
    -0.12
     elf
    -0.12
     Elves
    -0.12
     aliens
    -0.11
    punk
    -0.11
     menn
    -0.11
     shm
    -0.11
    POSITIVE LOGITS
     Tiger
    0.25
     tiger
    0.24
     Tigers
    0.23
     roar
    0.21
     lion
    0.20
     Lion
    0.20
     lions
    0.19
     Panther
    0.18
     roaring
    0.17
     Lions
    0.17
    Activations Density 0.505%

    No Known Activations