© 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. 26688
    Prev
    Next
    INDEX
    Explanations

    words ending in ing

    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
     Monument
    -0.10
    NDER
    -0.10
    arks
    -0.10
    enk
    -0.10
    iolet
    -0.10
    tors
    -0.10
    ync
    -0.10
    bserv
    -0.09
    ÂŃing
    -0.09
     headquartered
    -0.09
    POSITIVE LOGITS
     scaling
    0.11
     bounding
    0.11
     testing
    0.11
     thinking
    0.11
     blogging
    0.11
     ruling
    0.11
     sampling
    0.11
     scanning
    0.11
     booming
    0.11
     haunting
    0.11
    Activations Density 0.167%

    No Known Activations