© 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. 57321
    Prev
    Next
    INDEX
    Explanations

    code syntax and structure

    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
     alternating
    -0.12
     consecutive
    -0.12
    vary
    -0.11
     Altern
    -0.10
    /activity
    -0.10
     –↵↵
    -0.10
    anie
    -0.10
     Downs
    -0.09
    inity
    -0.09
     alteration
    -0.09
    POSITIVE LOGITS
     supplemented
    0.09
    ures
    0.08
     supplemental
    0.08
     elsewhere
    0.08
     clearance
    0.08
     +=
    0.08
     enlarg
    0.07
    aks
    0.07
    atura
    0.07
     aug
    0.07
    Activations Density 0.016%

    No Known Activations