© 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. 17
    Prev
    Next
    INDEX
    Explanations

    causes and explanations

    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
    daily
    -0.07
    pot
    -0.07
    Instructions
    -0.07
    lex
    -0.07
    singleton
    -0.07
     Muk
    -0.07
    extend
    -0.07
     confront
    -0.07
    eph
    -0.07
     aspire
    -0.07
    POSITIVE LOGITS
     causes
    0.20
     factors
    0.20
     reasons
    0.20
     explanation
    0.19
     explanations
    0.19
     underlying
    0.18
     caused
    0.17
     culprit
    0.17
     attributable
    0.17
     Reasons
    0.17
    Activations Density 2.250%

    No Known Activations