© 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. 112685
    Prev
    Next
    INDEX
    Explanations

    adjectives describing positive qualities

    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
    -blog
    -0.11
    -tags
    -0.11
     agenda
    -0.11
     toolkit
    -0.10
    uras
    -0.10
     dataset
    -0.10
     electorate
    -0.10
    ilyn
    -0.10
    quist
    -0.10
     autobiography
    -0.10
    POSITIVE LOGITS
     experiences
    0.21
     encounters
    0.21
     solutions
    0.19
     conversations
    0.18
     moments
    0.17
     interactions
    0.17
     insights
    0.17
     surprises
    0.16
     adventures
    0.16
     outcomes
    0.16
    Activations Density 0.154%

    No Known Activations