© 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. 29214
    Prev
    Next
    INDEX
    Explanations

    Dragon Ball, Dragon boat, Dragon China

    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
    ppe
    -0.12
     Trafford
    -0.11
     Shelley
    -0.11
    atus
    -0.11
    olla
    -0.10
    ollo
    -0.10
    elp
    -0.10
    vertiser
    -0.10
     Cecil
    -0.10
    pollo
    -0.10
    POSITIVE LOGITS
    fly
    0.17
    flies
    0.15
     dragons
    0.11
     Dragon
    0.11
     Dragons
    0.10
    Dragon
    0.10
    fruit
    0.10
    rid
    0.10
    dragon
    0.10
     dragon
    0.10
    Activations Density 0.003%

    No Known Activations