© 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. 48402
    Prev
    Next
    INDEX
    Explanations

    adverbs of degree followed by manner adverbs

    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
     very
    -0.11
    aida
    -0.10
     hugely
    -0.09
    usive
    -0.09
    argon
    -0.09
    azi
    -0.09
     greatly
    -0.09
     Very
    -0.09
    icable
    -0.08
     immensely
    -0.08
    POSITIVE LOGITS
     differently
    0.21
     anonymously
    0.14
    ynchronously
    0.13
     asynchronously
    0.13
     defensively
    0.13
     responsibly
    0.12
     forcefully
    0.12
    grily
    0.12
     unsuccessfully
    0.12
     efficiently
    0.12
    Activations Density 0.060%

    No Known Activations