© 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. 90783
    Prev
    Next
    INDEX
    Explanations

    driven by / powered by

    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
     pied
    -0.10
    beg
    -0.10
     Peace
    -0.09
     beg
    -0.09
    ordo
    -0.09
     wh
    -0.09
    amil
    -0.09
     salvation
    -0.08
    insky
    -0.08
     Boot
    -0.08
    POSITIVE LOGITS
     passion
    0.11
     imagination
    0.11
     trust
    0.10
     centuries
    0.10
     curiosity
    0.10
     empathy
    0.09
    osit
    0.09
     caffeine
    0.09
     keen
    0.09
     compassion
    0.09
    Activations Density 0.012%

    No Known Activations