© 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. 2015
    Prev
    Next
    INDEX
    Explanations

    .gov funding submission

    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
     prof
    -0.08
    .lesson
    -0.08
    /mat
    -0.08
    olie
    -0.08
     underlying
    -0.08
     cush
    -0.08
    ã
    -0.08
     Wikipedia
    -0.07
    avr
    -0.07
    (strict
    -0.07
    POSITIVE LOGITS
     Peg
    0.08
     Sands
    0.08
    Vectorizer
    0.08
    ellant
    0.08
    aneously
    0.08
    ELEMENT
    0.08
    edis
    0.07
     curso
    0.07
     Celt
    0.07
     Booster
    0.07
    Activations Density 5.673%

    No Known Activations