© 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. 6338
    Prev
    Next
    INDEX
    Explanations

    plural nouns and abbreviations

    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
    iciel
    -0.09
     Bourbon
    -0.09
     Franco
    -0.08
    ););↵
    -0.08
    éné
    -0.08
     Erdogan
    -0.08
    icional
    -0.08
    +offset
    -0.08
    eteor
    -0.08
    emale
    -0.08
    POSITIVE LOGITS
     IPs
    0.17
     TVs
    0.15
     Martins
    0.15
     PCs
    0.14
     Bengals
    0.14
    xies
    0.14
     Jerseys
    0.14
    addons
    0.13
     Crushers
    0.13
    trys
    0.13
    Activations Density 1.094%

    No Known Activations