© 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. 1512
    Prev
    Next
    INDEX
    Explanations

    more than

    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
    tron
    -0.10
    udu
    -0.09
     tutto
    -0.09
    ipi
    -0.09
    enc
    -0.09
    ilit
    -0.09
    arde
    -0.09
    ITE
    -0.08
    icut
    -0.08
     limitless
    -0.08
    POSITIVE LOGITS
     expected
    0.12
     usual
    0.12
     anticipated
    0.11
     mere
    0.11
     ever
    0.10
    -average
    0.10
    -ever
    0.10
     than
    0.10
    /e
    0.09
    urses
    0.09
    Activations Density 0.668%

    No Known Activations