© 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. 113540
    Prev
    Next
    INDEX
    Explanations

    spend time

    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
    atu
    -0.10
     Occup
    -0.10
     occupations
    -0.10
    ury
    -0.09
     Occupation
    -0.09
     shell
    -0.09
     Claw
    -0.09
     Gott
    -0.09
    \a
    -0.09
     occupied
    -0.09
    POSITIVE LOGITS
     time
    0.18
    time
    0.13
     evenings
    0.12
    æŶéĹ´
    0.11
     daylight
    0.10
     вÑĢемÑı
    0.10
     mornings
    0.10
     winters
    0.10
    stime
    0.09
    .time
    0.09
    Activations Density 0.024%

    No Known Activations