© 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. 16039
    Prev
    Next
    INDEX
    Explanations

    past tense verbs ending in -ed/-oke/-ore

    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
     enorm
    -0.12
    LY
    -0.12
    ly
    -0.11
    ity
    -0.11
    ITY
    -0.11
    esses
    -0.11
    ibu
    -0.10
    lays
    -0.10
    OUS
    -0.10
    hood
    -0.10
    POSITIVE LOGITS
    entimes
    0.12
    ster
    0.12
    sters
    0.11
    tober
    0.11
    ger
    0.11
    ed
    0.11
    ish
    0.10
    ter
    0.09
    -ish
    0.09
    site
    0.09
    Activations Density 0.102%

    No Known Activations