© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 115494
    Prev
    Next
    INDEX
    Explanations

    caramelized, caramelizing

    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
    erek
    -0.11
    enheim
    -0.09
    avers
    -0.09
     garment
    -0.09
    ularity
    -0.09
     prick
    -0.09
    yte
    -0.09
     stiff
    -0.08
     garments
    -0.08
    scape
    -0.08
    POSITIVE LOGITS
    ized
    0.18
    ised
    0.15
    ization
    0.15
    izable
    0.13
    isation
    0.12
    izing
    0.12
     popcorn
    0.11
    ixer
    0.11
    isable
    0.11
    icas
    0.10
    Activations Density 0.005%

    No Known Activations