© 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. 57870
    Prev
    Next
    INDEX
    Explanations

    code delimiters and operators

    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
    ker
    -0.09
     excludes
    -0.08
    ento
    -0.07
    opes
    -0.07
     unlikely
    -0.07
     nevertheless
    -0.07
     Knee
    -0.07
    antu
    -0.07
    ENT
    -0.07
     continents
    -0.07
    POSITIVE LOGITS
    alia
    0.11
    Ads
    0.10
    underline
    0.09
     profession
    0.09
     duplic
    0.09
     Woodward
    0.09
    iswa
    0.09
    rence
    0.09
    ClassName
    0.09
     gigs
    0.09
    Activations Density 0.029%

    No Known Activations