© 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. 14988
    Prev
    Next
    INDEX
    Explanations

    intensity or contrast

    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
     Cover
    -0.10
    Cover
    -0.10
    Disposition
    -0.10
    iah
    -0.10
    ño
    -0.09
     dismantle
    -0.09
     unpredictable
    -0.09
    transforms
    -0.09
     infinitely
    -0.09
     endless
    -0.09
    POSITIVE LOGITS
     exaggerated
    0.32
     exagger
    0.32
     pronounced
    0.25
     vivid
    0.24
     accent
    0.24
     intensified
    0.23
     sharpen
    0.22
     stark
    0.22
     clearer
    0.21
     extremes
    0.21
    Activations Density 0.202%

    No Known Activations