© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 92019
    Prev
    Next
    INDEX
    Explanations

    morning and evening times

    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
     cand
    -0.10
     Roo
    -0.09
     nighttime
    -0.09
     Wald
    -0.09
     afternoon
    -0.08
     morning
    -0.08
     chang
    -0.08
    996
    -0.08
     daytime
    -0.08
     –↵↵
    -0.08
    POSITIVE LOGITS
     glory
    0.15
     Glory
    0.14
     Gloria
    0.12
     beauty
    0.11
    exion
    0.11
     schön
    0.10
    stasy
    0.10
    ollipop
    0.10
     blossom
    0.10
     flowers
    0.10
    Activations Density 0.001%

    No Known Activations