© 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. 15561
    Prev
    Next
    INDEX
    Explanations

    cold 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
     wink
    -0.11
     peacefully
    -0.10
    /Index
    -0.10
     mower
    -0.10
     Pow
    -0.10
    Nu
    -0.10
     wil
    -0.09
    rez
    -0.09
    .me
    -0.09
    ppo
    -0.09
    POSITIVE LOGITS
    /free
    0.11
    ida
    0.10
    .tem
    0.10
    emit
    0.10
     eman
    0.10
     Winter
    0.10
     snaps
    0.10
    /fr
    0.09
     snap
    0.09
    ores
    0.09
    Activations Density 0.071%

    No Known Activations