© 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. 112508
    Prev
    Next
    INDEX
    Explanations

    menu and food topics

    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
    ogan
    -0.09
    anky
    -0.09
     Herz
    -0.08
     Frankfurt
    -0.08
     Roth
    -0.08
     sore
    -0.08
    415
    -0.08
     Ree
    -0.07
    ëħ
    -0.07
    utz
    -0.07
    POSITIVE LOGITS
    /dr
    0.16
    (food
    0.14
    /co
    0.13
    /sn
    0.12
     eaten
    0.12
     dishes
    0.11
    stuff
    0.11
     meals
    0.11
    /sm
    0.11
    /fast
    0.11
    Activations Density 0.531%

    No Known Activations