© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113598
    Prev
    Next
    INDEX
    Explanations

    holding, mouth, eating, retention

    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
     drinking
    -0.13
     feeding
    -0.12
    feeding
    -0.10
     feed
    -0.10
     fed
    -0.10
     hookup
    -0.10
     Feed
    -0.10
     Drinking
    -0.10
    Feed
    -0.10
    -feed
    -0.10
    POSITIVE LOGITS
     Held
    0.14
     held
    0.14
     hold
    0.14
     retaining
    0.13
     Bucc
    0.12
     retention
    0.12
     HOLD
    0.12
     holding
    0.12
     linger
    0.12
     Pron
    0.12
    Activations Density 0.043%

    No Known Activations