© 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. 32689
    Prev
    Next
    INDEX
    Explanations

    bold, italics, capitals, case

    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
    Suffix
    -0.12
     suffix
    -0.11
     Et
    -0.10
     appar
    -0.10
    Prefix
    -0.10
     Byte
    -0.10
     slash
    -0.10
     ç¬
    -0.10
    suffix
    -0.10
    prefix
    -0.10
    POSITIVE LOGITS
     bold
    0.21
     Bold
    0.17
     capitals
    0.16
    -bold
    0.16
     font
    0.15
    caps
    0.15
     capital
    0.15
    Bold
    0.15
     italic
    0.15
     caps
    0.14
    Activations Density 0.217%

    No Known Activations