© 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. 3158
    Prev
    Next
    INDEX
    Explanations

    semiconductor device or component

    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
    rides
    -0.10
    edom
    -0.10
    ania
    -0.10
    .usermodel
    -0.10
    itecture
    -0.10
    atis
    -0.09
    lij
    -0.09
    @↵↵
    -0.09
    ember
    -0.09
     Westbrook
    -0.09
    POSITIVE LOGITS
    oha
    0.09
    usk
    0.09
    alo
    0.08
    vault
    0.08
    vice
    0.08
    dea
    0.08
    ANGED
    0.08
    indsay
    0.07
    lbrace
    0.07
     Nexus
    0.07
    Activations Density 0.045%

    No Known Activations