© 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. 32726
    Prev
    Next
    INDEX
    Explanations

    monkeys, scientific names, specific words

    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
     EntityState
    -0.11
     Swal
    -0.11
    urat
    -0.11
     ducks
    -0.10
     lav
    -0.10
     dragon
    -0.10
     Keller
    -0.10
     Alexandria
    -0.10
    eyed
    -0.10
     duck
    -0.10
    POSITIVE LOGITS
     ape
    0.46
     monkey
    0.42
     Monkey
    0.39
     chimpan
    0.38
     monkeys
    0.37
     gor
    0.35
    Monkey
    0.34
     jungle
    0.31
     Jungle
    0.30
    monkey
    0.29
    Activations Density 0.584%

    No Known Activations