© 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. 6474
    Prev
    Next
    INDEX
    Explanations

    nocturnal, overnight, night, fasting, waking

    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
     commod
    -0.09
     shared
    -0.08
     nervous
    -0.08
     blackmail
    -0.08
    /shared
    -0.08
     nerv
    -0.08
     sle
    -0.08
     bare
    -0.08
     extern
    -0.07
     official
    -0.07
    POSITIVE LOGITS
     overnight
    0.21
     Overnight
    0.18
     morning
    0.17
     waking
    0.17
     mornings
    0.16
     noct
    0.15
     wakes
    0.15
     woke
    0.15
     Morning
    0.14
     wake
    0.14
    Activations Density 0.029%

    No Known Activations