© 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. 29978
    Prev
    Next
    INDEX
    Explanations

    started to discover passion

    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
     Platt
    -0.09
    ymb
    -0.08
    abis
    -0.08
    agus
    -0.08
     plaster
    -0.08
     unnamed
    -0.08
    unning
    -0.08
    ador
    -0.07
    431
    -0.07
     sweat
    -0.07
    POSITIVE LOGITS
     interest
    0.30
     Interest
    0.26
     interested
    0.25
    Interest
    0.24
    interest
    0.24
     passion
    0.22
     fascination
    0.21
    interested
    0.20
    Interested
    0.19
     Interested
    0.19
    Activations Density 0.366%

    No Known Activations