© 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. 54450
    Prev
    Next
    INDEX
    Explanations

    understandable

    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
    irie
    -0.11
     obt
    -0.10
    away
    -0.09
     Swarm
    -0.09
     slim
    -0.09
     discre
    -0.09
     Spiral
    -0.09
    odate
    -0.09
    UTE
    -0.09
    aza
    -0.09
    POSITIVE LOGITS
    orous
    0.08
    scan
    0.08
    eos
    0.08
     forg
    0.08
    atel
    0.07
    æĺĵ
    0.07
    uish
    0.07
     scan
    0.07
    ko
    0.07
    neau
    0.07
    Activations Density 0.035%

    No Known Activations