© 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. 15582
    Prev
    Next
    INDEX
    Explanations

    food related terms

    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
    ussen
    -0.08
     unofficial
    -0.07
    atomic
    -0.07
     HOT
    -0.07
     hot
    -0.06
    abbit
    -0.06
    olds
    -0.06
     Visibility
    -0.06
     IT
    -0.06
     Harley
    -0.06
    POSITIVE LOGITS
    borne
    0.15
    stuff
    0.14
    /feed
    0.14
     poisoning
    0.13
     Grade
    0.13
     allergies
    0.13
    /be
    0.13
     grade
    0.13
    service
    0.13
    -grade
    0.12
    Activations Density 0.029%

    No Known Activations