© 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. 89475
    Prev
    Next
    INDEX
    Explanations

    words ending in -s, -tion, or -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
    iques
    -0.12
    aises
    -0.12
    ses
    -0.12
    ares
    -0.12
    tures
    -0.12
    ches
    -0.11
    erais
    -0.11
     Proud
    -0.11
    asts
    -0.11
    (es
    -0.11
    POSITIVE LOGITS
    ://
    0.10
     groups
    0.09
     packs
    0.09
    ince
    0.09
     hops
    0.09
    ster
    0.08
    orry
    0.08
    uch
    0.08
    -rights
    0.08
     proportions
    0.08
    Activations Density 0.296%

    No Known Activations