© 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. 207
    Prev
    Next
    INDEX
    Explanations

    java and c++ programming constructs

    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
    /if
    -0.09
    ardon
    -0.08
    .renderer
    -0.07
    fan
    -0.07
     HuffPost
    -0.07
     polic
    -0.07
    .dc
    -0.07
    ToLocal
    -0.07
    zz
    -0.07
     newArray
    -0.07
    POSITIVE LOGITS
    Impl
    0.14
     class
    0.13
     íģ´ëŀĺìĬ¤
    0.13
    _Impl
    0.13
    ç±»
    0.12
    .from
    0.11
    .prototype
    0.11
    -class
    0.11
     Class
    0.11
     constructor
    0.10
    Activations Density 1.823%

    No Known Activations