© 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. 112874
    Prev
    Next
    INDEX
    Explanations

    lunch time activities

    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
    quin
    -0.09
    anni
    -0.09
    ÌĢ
    -0.08
     breakfast
    -0.08
     Panc
    -0.08
     lat
    -0.08
     def
    -0.08
     customary
    -0.08
    ulously
    -0.08
     preserve
    -0.08
    POSITIVE LOGITS
    time
    0.23
    room
    0.17
    -time
    0.16
    (es
    0.16
    day
    0.14
    box
    0.14
    rooms
    0.14
    ing
    0.13
    ables
    0.13
    esi
    0.13
    Activations Density 0.010%

    No Known Activations