© 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. 54584
    Prev
    Next
    INDEX
    Explanations

    random number generation

    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
     unpredict
    -0.11
     randomly
    -0.11
     random
    -0.10
    -random
    -0.10
     unpredictable
    -0.09
    irling
    -0.09
    _random
    -0.09
     Random
    -0.09
    미
    -0.09
    GIN
    -0.09
    POSITIVE LOGITS
    kie
    0.12
    (found
    0.09
    pf
    0.09
    ento
    0.09
     Mold
    0.08
    itta
    0.08
    bie
    0.08
    stan
    0.08
     mend
    0.08
    ôme
    0.08
    Activations Density 0.006%

    No Known Activations