© 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. 4616
    Prev
    Next
    INDEX
    Explanations

    operation level

    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
    anium
    -0.10
    beg
    -0.09
     obs
    -0.09
    ogan
    -0.09
    -bound
    -0.09
    parallel
    -0.09
     cases
    -0.09
     Bedroom
    -0.08
    rol
    -0.08
    buffer
    -0.08
    POSITIVE LOGITS
     level
    0.15
     outset
    0.14
     helm
    0.14
     glance
    0.13
     jun
    0.12
     expense
    0.12
     discretion
    0.12
     point
    0.11
     junction
    0.11
     pace
    0.11
    Activations Density 0.411%

    No Known Activations