© 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. 905
    Prev
    Next
    INDEX
    Explanations

    measurement techniques and imaging

    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
     researched
    -0.10
    ullo
    -0.10
     governing
    -0.10
    _WARNINGS
    -0.10
     factories
    -0.09
     Pare
    -0.09
     dereg
    -0.09
    /functions
    -0.09
     cic
    -0.09
    prog
    -0.09
    POSITIVE LOGITS
     measuring
    0.17
     measurement
    0.17
     measurements
    0.16
     detecting
    0.15
     instrumentation
    0.15
     data
    0.14
     instruments
    0.14
     recording
    0.14
     probing
    0.14
     scanning
    0.14
    Activations Density 4.238%

    No Known Activations