© 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. 25806
    Prev
    Next
    INDEX
    Explanations

    adverbs of frequency and typicality

    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
    odi
    -0.10
     Glad
    -0.10
     blister
    -0.09
     plunged
    -0.09
     dobr
    -0.09
    odo
    -0.09
     effort
    -0.09
     constituent
    -0.08
     efforts
    -0.08
    omed
    -0.08
    POSITIVE LOGITS
     typically
    0.25
     usually
    0.24
     Typically
    0.22
    typically
    0.21
     normally
    0.20
     Usually
    0.20
     generally
    0.19
    Usually
    0.19
    usually
    0.18
    Typ
    0.18
    Activations Density 0.068%

    No Known Activations