© 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. 1409
    Prev
    Next
    INDEX
    Explanations

    implementing the process

    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
    /*/
    -0.10
    ""↵
    -0.10
     además
    -0.09
     Himself
    -0.09
    TK
    -0.09
    atura
    -0.08
    oya
    -0.08
    THR
    -0.08
    .Framework
    -0.08
     Payne
    -0.08
    POSITIVE LOGITS
     this
    0.38
     these
    0.38
    è¿Ļ
    0.31
    this
    0.28
    these
    0.28
    æѤ
    0.26
     ÑįÑĤ
    0.24
    	this
    0.23
    ses
    0.22
     such
    0.21
    Activations Density 3.557%

    No Known Activations