© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 552
    Prev
    Next
    INDEX
    Explanations

    punctuation after word fragments

    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
    /filepath
    -0.11
    ies
    -0.10
    IE
    -0.10
    oya
    -0.10
    AP
    -0.10
    lasses
    -0.10
    imientos
    -0.10
     culpa
    -0.10
    bish
    -0.10
    ames
    -0.09
    POSITIVE LOGITS
     grav
    0.06
    inst
    0.06
    gn
    0.06
     hurd
    0.06
     is
    0.06
     afin
    0.06
    alia
    0.06
    phere
    0.06
    owe
    0.06
    iner
    0.06
    Activations Density 1.053%

    No Known Activations