© 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. 50564
    Prev
    Next
    INDEX
    Explanations

    prey upon or target

    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
     bri
    -0.11
    ufen
    -0.10
    odega
    -0.10
     Payments
    -0.10
    atest
    -0.10
     consortium
    -0.10
     trib
    -0.09
    alli
    -0.09
     controvers
    -0.09
     reconc
    -0.09
    POSITIVE LOGITS
     prey
    0.23
     targeting
    0.20
     target
    0.19
     targets
    0.19
    -target
    0.19
    /target
    0.19
     predatory
    0.18
     targeted
    0.18
    target
    0.18
     predators
    0.17
    Activations Density 0.067%

    No Known Activations