© 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. 3243
    Prev
    Next
    INDEX
    Explanations

    types of methods and techniques

    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
     aim
    -0.10
    Spin
    -0.10
    iry
    -0.10
    ndern
    -0.10
    bindings
    -0.10
    ispers
    -0.10
     spin
    -0.10
    emplace
    -0.10
    spin
    -0.10
     vera
    -0.09
    POSITIVE LOGITS
     lies
    0.11
    lie
    0.09
    sei
    0.09
    idis
    0.08
     is
    0.08
     resides
    0.08
     surrounds
    0.08
    ifu
    0.07
    occ
    0.07
     occurs
    0.07
    Activations Density 0.268%

    No Known Activations