© 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. 3195
    Prev
    Next
    INDEX
    Explanations

    Roman numerals and suffixes

    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
     Frid
    -0.11
    ican
    -0.10
    ixa
    -0.10
    ocode
    -0.10
     Rhino
    -0.09
     neighb
    -0.09
    ?><
    -0.09
    ua
    -0.09
     Ef
    -0.09
    .oc
    -0.09
    POSITIVE LOGITS
     Jr
    0.21
     II
    0.19
     jr
    0.16
    II
    0.16
     III
    0.16
     Sr
    0.15
     ii
    0.13
     junior
    0.13
    ii
    0.13
    III
    0.12
    Activations Density 0.499%

    No Known Activations