© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 27261
    Prev
    Next
    INDEX
    Explanations

    expressing thanks

    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
    acia
    -0.09
     reck
    -0.09
    afs
    -0.08
    anza
    -0.08
     nuit
    -0.08
    chu
    -0.08
    viar
    -0.07
    osp
    -0.07
    NU
    -0.07
    186
    -0.07
    POSITIVE LOGITS
     thank
    0.98
     thanks
    0.88
     Thank
    0.82
     thanked
    0.80
     Thanks
    0.75
     THANK
    0.75
    Thank
    0.75
     thanking
    0.73
    thank
    0.72
    Thanks
    0.68
    Activations Density 1.074%

    No Known Activations