© 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. 2030
    Prev
    Next
    INDEX
    Explanations

    keep something intact or unchanged

    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
     nearest
    -0.09
     beginning
    -0.09
     Beginning
    -0.09
    reed
    -0.08
    ROL
    -0.08
    kre
    -0.08
    (AP
    -0.08
    .bz
    -0.08
    ANE
    -0.08
     beginnings
    -0.08
    POSITIVE LOGITS
     intact
    0.20
    alive
    0.19
     track
    0.18
    ders
    0.18
     abre
    0.17
     unchanged
    0.16
     pace
    0.16
     alive
    0.15
     indefinitely
    0.14
    AspectRatio
    0.14
    Activations Density 0.705%

    No Known Activations