© 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. 56728
    Prev
    Next
    INDEX
    Explanations

    numbers followed by zeros

    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
    не
    -0.10
    rene
    -0.09
    ève
    -0.09
     tie
    -0.09
    oud
    -0.09
    cona
    -0.09
     Matter
    -0.09
    ichten
    -0.09
     matter
    -0.09
    POSITIVE LOGITS
    000
    0.11
    00
    0.09
    999
    0.09
     outfit
    0.08
    XXX
    0.08
     mmc
    0.08
    100
    0.07
    dess
    0.07
     Oval
    0.07
    /ge
    0.07
    Activations Density 0.023%

    No Known Activations