© 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. 57491
    Prev
    Next
    INDEX
    Explanations

    numbers after certain markers

    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
    sti
    -0.09
     Lun
    -0.09
     Sav
    -0.09
    istas
    -0.09
     bunk
    -0.09
    hof
    -0.08
     Bowen
    -0.08
     Fir
    -0.08
     Moving
    -0.08
     Lay
    -0.08
    POSITIVE LOGITS
    utable
    0.09
    ij
    0.08
     tol
    0.08
     addslashes
    0.07
    ambi
    0.07
    uxtap
    0.07
    wallet
    0.07
     /*!
    0.07
    ientes
    0.07
     côt
    0.07
    Activations Density 0.041%

    No Known Activations