© 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. 29798
    Prev
    Next
    INDEX
    Explanations

    -ing suffix

    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
    -ie
    -0.13
    lep
    -0.10
    inka
    -0.10
     Tic
    -0.10
    icons
    -0.10
    ETA
    -0.10
    ,tr
    -0.10
    ief
    -0.10
    .ie
    -0.10
    lug
    -0.10
    POSITIVE LOGITS
    haus
    0.11
    -ing
    0.10
    e
    0.10
    ding
    0.09
    ton
    0.09
    a
    0.09
    ways
    0.09
    dorf
    0.08
    arde
    0.08
    way
    0.08
    Activations Density 0.077%

    No Known Activations