© 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. 117146
    Prev
    Next
    INDEX
    Explanations

    twilight sleep

    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
     Dias
    -0.08
    site
    -0.08
     embedded
    -0.08
     Medina
    -0.08
     Kart
    -0.07
     stark
    -0.07
     spit
    -0.07
     duty
    -0.07
    asy
    -0.07
    sites
    -0.07
    POSITIVE LOGITS
    -zone
    0.15
    ê°Ħ
    0.15
     Zone
    0.14
     zone
    0.14
    geist
    0.12
    alley
    0.12
    zone
    0.12
    _zone
    0.11
     sparkle
    0.11
    éĸĵ
    0.11
    Activations Density 0.003%

    No Known Activations