© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 50225
    Prev
    Next
    INDEX
    Explanations

    adverb following capitalized word

    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
     critiques
    -0.11
     irgend
    -0.11
     Sacr
    -0.10
    akit
    -0.10
     tucked
    -0.10
     catastrophic
    -0.10
     slapped
    -0.10
     quoi
    -0.10
     canned
    -0.10
     things
    -0.10
    POSITIVE LOGITS
     furthermore
    0.14
     thanks
    0.14
     additionally
    0.13
     moreover
    0.13
     âĢŀ
    0.12
     duly
    0.12
     thereby
    0.12
     owing
    0.12
     EUR
    0.11
    Thanks
    0.11
    Activations Density 3.157%

    No Known Activations