© 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. 113108
    Prev
    Next
    INDEX
    Explanations

    times of day

    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
     rel
    -0.09
     slightest
    -0.09
    uisse
    -0.08
     protections
    -0.08
    merce
    -0.08
     pity
    -0.08
    ever
    -0.08
     overs
    -0.08
    skins
    -0.08
     Morr
    -0.08
    POSITIVE LOGITS
     afternoon
    0.11
     sunshine
    0.11
    -after
    0.11
     Starr
    0.10
     morning
    0.10
     mañana
    0.10
    Telegram
    0.10
    oken
    0.10
    pte
    0.09
     glow
    0.09
    Activations Density 0.001%

    No Known Activations