© 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. 50219
    Prev
    Next
    INDEX
    Explanations

    warm or cold weather

    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
     cooler
    -0.18
     cold
    -0.18
     Cold
    -0.17
     chilly
    -0.16
    cold
    -0.16
    Cold
    -0.15
     Cooling
    -0.15
     winters
    -0.15
     Cool
    -0.15
     colder
    -0.14
    POSITIVE LOGITS
     warmer
    0.29
     warm
    0.28
     Warm
    0.24
     thaw
    0.23
    Warm
    0.23
     warmed
    0.22
     warmth
    0.22
    warm
    0.20
     warming
    0.19
     sunny
    0.18
    Activations Density 0.601%

    No Known Activations