© 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. 3660
    Prev
    Next
    INDEX
    Explanations

    Node structure or MM

    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
     branches
    -0.08
     end
    -0.08
     related
    -0.07
     Branch
    -0.07
     Mort
    -0.07
     book
    -0.07
    Branch
    -0.07
     borders
    -0.07
    Related
    -0.07
     fly
    -0.07
    POSITIVE LOGITS
    atti
    0.11
    amble
    0.10
    ouri
    0.10
    olio
    0.10
    .testing
    0.10
    opo
    0.09
    �s
    0.09
    obe
    0.09
    pering
    0.09
    Aqu
    0.09
    Activations Density 0.269%

    No Known Activations