© 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. 115970
    Prev
    Next
    INDEX
    Explanations

    -ing / -ting endings

    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
    hare
    -0.12
    apesh
    -0.10
     Mitchell
    -0.10
     Vit
    -0.10
    vant
    -0.10
     domestically
    -0.10
    iores
    -0.09
    nesota
    -0.09
     Mart
    -0.09
     Jak
    -0.09
    POSITIVE LOGITS
    ing
    0.29
    ings
    0.25
    ING
    0.24
    ting
    0.24
    ging
    0.24
    ming
    0.21
    ning
    0.20
    ingt
    0.20
    ening
    0.19
    bing
    0.19
    Activations Density 0.221%

    No Known Activations