© 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. 25353
    Prev
    Next
    INDEX
    Explanations

    asleep, awake, sleep, dead

    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
     Debian
    -0.09
     disproportion
    -0.07
     crawling
    -0.07
    -depend
    -0.07
     tomorrow
    -0.07
     uz
    -0.07
     heir
    -0.06
     meal
    -0.06
     chrome
    -0.06
     pist
    -0.06
    POSITIVE LOGITS
     asleep
    0.28
     awake
    0.23
     sleeping
    0.20
     sleeps
    0.19
     sleep
    0.19
     dead
    0.18
     Sleeping
    0.18
    sleep
    0.17
    leep
    0.17
     pretended
    0.16
    Activations Density 0.055%

    No Known Activations