© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 4703
    Prev
    Next
    INDEX
    Explanations

    verbs followed by auxiliaries or adjectives

    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
     ath
    -0.10
    µľ
    -0.09
     ones
    -0.09
     housing
    -0.09
    kas
    -0.09
     Friedman
    -0.08
    /--
    -0.08
    Collapse
    -0.08
    esi
    -0.08
    iran
    -0.08
    POSITIVE LOGITS
     king
    0.12
     everywhere
    0.10
     kings
    0.09
     Incorporated
    0.09
    ehr
    0.09
     plentiful
    0.09
    ammer
    0.09
     queen
    0.08
     abound
    0.08
    IPH
    0.08
    Activations Density 0.662%

    No Known Activations