© 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. 55355
    Prev
    Next
    INDEX
    Explanations

    finding rules and patterns

    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
    opers
    -0.09
     tunnel
    -0.09
    obbies
    -0.09
     Hayward
    -0.08
    eday
    -0.08
    verture
    -0.08
     Extras
    -0.08
    .slide
    -0.08
     Tunnel
    -0.08
    ergy
    -0.08
    POSITIVE LOGITS
     rule
    0.21
     pattern
    0.18
     Rule
    0.18
     rules
    0.18
    Rule
    0.18
    rule
    0.17
     Rules
    0.17
     Pattern
    0.17
     RULE
    0.15
    -rule
    0.15
    Activations Density 0.208%

    No Known Activations