© 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. 4210
    Prev
    Next
    INDEX
    Explanations

    which or and

    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
    edis
    -0.08
    (){}↵↵
    -0.08
    uese
    -0.08
    dre
    -0.07
     add
    -0.07
    ocre
    -0.07
    dsl
    -0.07
    Łèĥ½
    -0.07
     furthermore
    -0.07
     if
    -0.07
    POSITIVE LOGITS
    Which
    0.12
     Which
    0.12
     And
    0.12
    Including
    0.11
     wich
    0.11
     Or
    0.11
    Cause
    0.11
    And
    0.11
     Especially
    0.10
     Including
    0.10
    Activations Density 0.413%

    No Known Activations