© 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. 26839
    Prev
    Next
    INDEX
    Explanations

    feeling positive, confident, or improved

    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
     immediately
    -0.10
     assumed
    -0.10
     brilliance
    -0.10
    ĥģ
    -0.10
     Cute
    -0.10
    Anywhere
    -0.09
    /original
    -0.09
     unsuccessfully
    -0.09
     pretext
    -0.09
     genius
    -0.09
    POSITIVE LOGITS
     confident
    0.19
     confidently
    0.19
     healthier
    0.18
     confidence
    0.17
     happier
    0.16
     thankful
    0.15
     thankfully
    0.14
     proudly
    0.14
     stronger
    0.14
     grateful
    0.14
    Activations Density 0.207%

    No Known Activations