© 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. 29851
    Prev
    Next
    INDEX
    Explanations

    urge to do something

    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
    ude
    -0.10
    unic
    -0.10
    ICS
    -0.09
    ayer
    -0.09
     Bellev
    -0.09
     umbrella
    -0.09
    uting
    -0.08
    VA
    -0.08
    ners
    -0.08
    800
    -0.08
    POSITIVE LOGITS
    éo
    0.12
    geber
    0.11
    Ur
    0.11
    prung
    0.10
     toward
    0.10
    urge
    0.10
     towards
    0.10
     urge
    0.10
     Ur
    0.10
    ual
    0.10
    Activations Density 0.006%

    No Known Activations