© 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. 55354
    Prev
    Next
    INDEX
    Explanations

    Sol words

    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
    ei
    -0.09
    her
    -0.09
    board
    -0.09
    IZES
    -0.09
    head
    -0.09
     bundles
    -0.09
    elia
    -0.08
    sov
    -0.08
     Matth
    -0.08
    forth
    -0.08
    POSITIVE LOGITS
    vents
    0.09
    unge
    0.08
    erno
    0.08
     midnight
    0.08
    nis
    0.07
    ilor
    0.07
    corn
    0.07
     Scripts
    0.07
     Lind
    0.07
    oons
    0.07
    Activations Density 0.012%

    No Known Activations