© 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. 7069
    Prev
    Next
    INDEX
    Explanations

    transformation or conversion

    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
     incidental
    -0.09
    pty
    -0.09
     Elevated
    -0.08
     Mosque
    -0.08
     omitted
    -0.08
     holders
    -0.08
     handshake
    -0.08
     sha
    -0.08
    afi
    -0.08
    grab
    -0.08
    POSITIVE LOGITS
     conversion
    0.19
     permanently
    0.19
     transformation
    0.18
    conversion
    0.16
     Conversion
    0.16
     conversions
    0.16
     convert
    0.15
     makeover
    0.15
     surg
    0.15
     Transformation
    0.15
    Activations Density 0.031%

    No Known Activations