© 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. 4641
    Prev
    Next
    INDEX
    Explanations

    temporal prepositional phrases

    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
    upp
    -0.10
    uida
    -0.10
     âĢ¦↵↵
    -0.09
    andal
    -0.09
    rips
    -0.09
    [âĢ¦
    -0.09
     Interr
    -0.09
    (fabs
    -0.09
     quits
    -0.08
    .fm
    -0.08
    POSITIVE LOGITS
     presumably
    0.09
     say
    0.09
    say
    0.08
     perhaps
    0.08
     nam
    0.08
     Nam
    0.08
    она
    0.08
    ender
    0.08
    cho
    0.08
     namely
    0.08
    Activations Density 0.393%

    No Known Activations