© 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. 54547
    Prev
    Next
    INDEX
    Explanations

    organization and concepts

    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
     successive
    -0.09
    alfa
    -0.09
     Entrance
    -0.09
    rips
    -0.08
    -č↵
    -0.08
     Incre
    -0.08
    mus
    -0.08
    mpr
    -0.08
    ric
    -0.08
    agine
    -0.08
    POSITIVE LOGITS
    ops
    0.09
     suite
    0.08
    uale
    0.08
     moons
    0.08
     Lindsay
    0.08
     burden
    0.07
     remainder
    0.07
     display
    0.07
    irm
    0.07
     =='
    0.07
    Activations Density 0.234%

    No Known Activations