© 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. 18204
    Prev
    Next
    INDEX
    Explanations

    wind and damage

    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
     winds
    -0.21
     Winds
    -0.18
     wind
    -0.16
     Wind
    -0.16
     windy
    -0.16
     breeze
    -0.13
    Wind
    -0.13
     airflow
    -0.12
    wind
    -0.11
     Glover
    -0.11
    POSITIVE LOGITS
     asymmetric
    0.10
     lee
    0.10
     trees
    0.10
    _LD
    0.09
     Batt
    0.09
     tree
    0.09
     sail
    0.09
     kite
    0.09
     UNC
    0.09
     unprotected
    0.09
    Activations Density 0.138%

    No Known Activations