© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 55993
    Prev
    Next
    INDEX
    Explanations

    contribution and expenditure

    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
    tea
    -0.10
    /co
    -0.09
     presidential
    -0.09
    edia
    -0.09
     warmed
    -0.09
    Throw
    -0.09
    erne
    -0.09
    erville
    -0.09
     hom
    -0.09
     chemistry
    -0.09
    POSITIVE LOGITS
     Contribution
    0.12
     contribute
    0.12
     contribution
    0.12
     Contrib
    0.12
     contributes
    0.11
     contributions
    0.11
    Contrib
    0.10
     CONTRIBUT
    0.10
     contributing
    0.10
     Contributions
    0.10
    Activations Density 0.143%

    No Known Activations