© 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-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 3673
    Prev
    Next
    INDEX
    Explanations

    plural nouns ending in s

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rond
    -0.11
    pot
    -0.10
     POLITICO
    -0.10
    noch
    -0.10
     dash
    -0.10
    _RC
    -0.10
    olson
    -0.10
    >č↵č↵č↵
    -0.10
    ettel
    -0.10
    iciel
    -0.10
    POSITIVE LOGITS
    ads
    0.07
    ebb
    0.07
     Kaiser
    0.07
     Bip
    0.07
    ingly
    0.07
    mer
    0.06
     rop
    0.06
     vision
    0.06
     assorted
    0.06
    oft
    0.06
    Activations Density 0.477%

    No Known Activations