© 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. 55377
    Prev
    Next
    INDEX
    Explanations

    rounding numbers

    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
    UB
    -0.09
    ?type
    -0.08
     prop
    -0.08
    openh
    -0.08
    ocate
    -0.08
    ,copy
    -0.07
    itaire
    -0.07
     royalty
    -0.07
    ocking
    -0.07
    charts
    -0.07
    POSITIVE LOGITS
    lis
    0.10
    Lv
    0.09
     quarters
    0.09
    rq
    0.09
     Ingredients
    0.09
    ¡°
    0.09
    /spec
    0.09
    اد
    0.09
     Luis
    0.09
     PROF
    0.09
    Activations Density 0.001%

    No Known Activations