© 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. 3671
    Prev
    Next
    INDEX
    Explanations

    competitor vs competitor

    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
    ож
    -0.09
    utow
    -0.08
    /ws
    -0.08
    kek
    -0.08
     Flames
    -0.08
     ec
    -0.07
    illo
    -0.07
     ecstatic
    -0.07
     {↵↵↵↵
    -0.07
     customs
    -0.07
    POSITIVE LOGITS
     competing
    0.19
     competitors
    0.19
     rival
    0.18
     competitor
    0.18
     rivals
    0.16
     contenders
    0.15
     Compet
    0.13
     fron
    0.12
     competition
    0.11
     contender
    0.11
    Activations Density 0.324%

    No Known Activations