© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 90611
    Prev
    Next
    INDEX
    Explanations

    high temperatures

    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
     night
    -0.15
     Night
    -0.13
     nightly
    -0.13
     nights
    -0.13
    -night
    -0.13
     spontaneously
    -0.13
     NIGHT
    -0.12
     Nights
    -0.12
    night
    -0.12
    Night
    -0.12
    POSITIVE LOGITS
     overhead
    0.19
     heat
    0.17
     noon
    0.17
     hottest
    0.16
     hotter
    0.15
     heating
    0.13
    heat
    0.13
    Heat
    0.13
     parch
    0.13
     Heat
    0.13
    Activations Density 0.093%

    No Known Activations