© 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. 8501
    Prev
    Next
    INDEX
    Explanations

    specific prepositions before dates/locations

    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
    akhir
    -0.07
    overe
    -0.06
    LEX
    -0.06
     Spiel
    -0.06
     zach
    -0.06
     Yosemite
    -0.06
     nik
    -0.06
    ometown
    -0.06
    ë¦
    -0.06
    erb
    -0.06
    POSITIVE LOGITS
    该
    0.17
     therein
    0.13
    ibs
    0.13
    ib
    0.13
    ran
    0.10
     thereof
    0.10
     dort
    0.10
     abbreviated
    0.10
     rang
    0.10
    CMS
    0.10
    Activations Density 1.393%

    No Known Activations